High Force Density Gripping with UV Activation and Sacrificial Adhesion
Lee, Esther North Carolina State University, Goddard, Zachary Georgia Institute of Technology, Ngotiaoco, Joshua Georgia Institute of Technology, Monterrosa, Noe Georgia Institute of Technology Mazumdar, Anirban Georgia Institute of Technology
Keywords: Mechanism Design, Mobile Manipulation
Abstract: This paper presents a novel physical gripping framework intended for controlled, high force density attachment on a range of surfaces. Our framework utilizes a light-activated chemical adhesive to attach to surfaces. The cured adhesive is part of a “sacrificial layer,” which is shed when the gripper separates from the surface. In order to control adhesive behavior we utilize ultraviolet (UV) light sensitive acrylics which are capable of rapid curing when activated with 380nm light. Once cured, zero input power is needed to hold load. Thin plastic parts can be used as the sacrificial layers, and these can be released using an electric motor. This new gripping framework including the curing load capacity, adhesive deposition, and sacrificial methods are described in detail. Two proof-of concept prototypes are designed, built, and tested. The experimental results illustrate the response time (15-75s depending on load), high holding force density (10-30), and robustness to material type. Additionally, two drawbacks of this design are discussed: corruption of the gripped surface and a limited number of layers.
Using Manipulation to Enable Adaptive Ground Mobility
Kim, Raymond Georgia Institute of Technology, DeBate, Alex Georgia Institute of Technology, Balakirsky, Stephen Georgia Institute of Technology, Mazumdar, Anirban Georgia Institute of Technology
Keywords: Mechanism Design, Mobile Manipulation, Wheeled Robots
Abstract: In order to accomplish various missions, autonomous ground vehicles must operate on a wide range of terrain. While many systems such as wheels and whegs can navigate some types of terrain, none are optimal across all. This creates a need for physical adaptation. This paper presents a broad new approach to physical adaptation that relies on manipulation. Specifically, we explore how multipurpose manipulators can enable ground vehicles to dramatically modify their propulsion system in order to optimize performance across various terrain. While this approach is general and widely applicable, this work focuses on physically switching between wheels and legs. We outline the design of “swappable propulsors” that combine the powerful adhesion forces of permanent magnets with geometric features for easy detachment. We provide analysis on how the swappable propulsors can be manipulated, and use these results to create a functional prototype robot. This robot can use its manipulator to change between wheeled and legged locomotion. Our experimental results illustrate how this approach can enhance energy efficiency and versatility.
Closed-Loop Benchmarking of Stereo Visual-Inertial SLAM Systems: Understanding the Impact of Drift and Latency on Tracking Accuracy
Zhao, Yipu Facebook Inc, Smith, Justin Georgia Institute of Technology Karumanchi, Sambhu Harimanas National Institute of Technology Karnataka, Surathkal Vela, Patricio Georgia Institute of Technology
Keywords: SLAM, Performance Evaluation and Benchmarking, Localization
Abstract: Visual-inertial SLAM is essential for robot navigation in GPS-denied environments, e.g. indoor, underground. Conventionally, the performance of visual-inertial SLAM is evaluated with open-loop analysis, with a focus on the drift level of SLAM systems. In this paper, we raise the question on the importance of visual estimation latency in closed-loop navigation tasks, such as accurate trajectory tracking. To understand the impact of both drift and latency on visual-inertial SLAM systems, a closed-loop benchmarking simulation is conducted, where a robot is commanded to follow a desired trajectory using the feedback from visual-inertial estimation. By extensively evaluating the trajectory tracking performance of representative state-of-the-art visual-inertial SLAM systems, we reveal the importance of latency reduction in visual estimation module of these systems. The findings suggest directions of future improvements for visual-inertial SLAM.
Human-Centric Active Perception for Autonomous Observation
Kent, David Georgia Institute of Technology Chernova, Sonia Georgia Institute of Technology
Keywords: Space Robotics and Automation, Human-Centered Robotics, Planning, Scheduling and Coordination
Abstract: As robot autonomy improves, robots are increasingly being considered in the role of autonomous observation systems — free-flying cameras capable of actively tracking human activity within some predefined area of interest. In this work, we formulate the autonomous observation problem through multi-objective optimization, presenting a novel Semi-MDP formulation of the autonomous human observation problem that maximizes observation rewards while accounting for both human- and robot-centric costs. We demonstrate that the problem can be solved with both scalarization-based Multi-Objective MDP methods and Constrained MDP methods, and discuss the relative benefits of each approach. We validate our work on activity tracking using a NASA Astrobee robot operating within a simulated International Space Station environment.
Constrained Sampling-Based Trajectory Optimization Using Stochastic Approximation
Boutselis, George Georgia Tech Wang, Ziyi Georgia Institute of Technology Theodorou, Evangelos Georgia Institute of Technology
Keywords: Optimization and Optimal Control, Collision Avoidance, Probability and Statistical Methods
Abstract: We propose a sampling-based trajectory optimization methodology for constrained problems. We extend recent works on stochastic search to deal with box control constraints, as well as nonlinear state constraints for discrete dynamical systems. Regarding the former, our strategy is to optimize over truncated parameterized distributions on control inputs. Furthermore, we show how non-smooth penalty functions can be incorporated into our framework to handle state constraints. Numerical simulations show that our approach outperforms previous methods on constrained sampling-based optimization, in terms of quality of solutions and sample efficiency.
CAGE: Context-Aware Grasping Engine
Liu, Weiyu Georgia Institute of Technology Daruna, Angel Georgia Institute of Technology Chernova, Sonia Georgia Institute of Technology
Keywords: Grasping, Perception for Grasping and Manipulation, Deep Learning in Robotics and Automation
Abstract:Semantic grasping is the problem of selecting stable grasps that are functionally suitable for specific object manipulation tasks. In order for robots to effectively perform object manipulation, a broad sense of contexts, including object and task constraints, needs to be accounted for. We introduce the Context-Aware Grasping Engine, which combines a novel semantic representation of grasp contexts with a neural network structure based on the Wide & Deep model, capable of capturing complex reasoning patterns. We quantitatively validate our approach against three prior methods on a novel dataset consisting of 14,000 semantic grasps for 44 objects, 7 tasks, and 6 different object states. Our approach outperformed all baselines by statistically significant margins, producing new insights into the importance of balancing memorization and generalization of contexts for semantic grasping. We further demonstrate the effectiveness of our approach on robot experiments in which the presented model successfully achieved 31 of 32 suitable grasps. The code and data are available at: https://github.com/wliu88/rail_semantic_grasping
EgoTEB: Egocentric, Perception Space Navigation Using Timed-Elastic-Bands
Smith, Justin Georgia Institute of Technology Xu, Ruoyang Georgia Institute of Technology Vela, Patricio Georgia Institute of Technology
Keywords:Visual-Based Navigation, Collision Avoidance, Motion and Path Planning
Abstract: The TEB hierarchical planner for real-time navigation through unknown environments is highly effective at balancing collision avoidance with goal directed motion. Designed over several years and publications, it implements a multi-trajectory optimization based synthesis method for identifying topologically distinct trajectory candidates through navigable space. Unfortunately, the underlying factor graph approach to the optimization problem induces a mismatch between grid-based representations and the optimization graph, which leads to several time and optimization inefficiencies. This paper explores the impact of using egocentric, perception space representations for the local planning map. Doing so alleviates many of the identified issues related to TEB and leads to a new method called egoTEB. Timing experiments and Monte Carlo evaluations in benchmark worlds quantify the benefits of egoTEB for navigation through uncertain environments.
Exploiting Singular Configurations for Controllable, Low-Power, Friction Enhancement on Unmanned Ground Vehicles
Foris, Adam Georgia Institute of Technology Wagener, Nolan Georgia Tech Boots, Byron University of Washington Mazumdar, Anirban Georgia Institute of Technology
Keywords: Mechanism Design, Field Robots, Wheeled Robots
Abstract: This paper describes the design, validation, and performance of a new type of adaptive wheel morphology for unmanned ground vehicles. Our adaptive wheel morphology uses a spiral cam to create a system that enables controllable deployment of high friction surfaces. The overall design is modular, battery powered, and can be mounted directly to the wheels of a vehicle without additional wiring. The use of a tailored cam profile exploits a singular configuration to minimize power consumption when deployed and protects the actuator from external forces. Component-level experiments demonstrate that friction on ice and grass can be increased by up to 170%. Two prototypes were also incorporated directly into a 1:5 scale radio-controlled rally car. The devices were able to controllably deploy, increase friction, and greatly improve acceleration capacity on a slippery, synthetic ice surface.
Image-Based Place Recognition on Bucolic Environment across Seasons from Semantic Edge Description
Benbihi, Assia Umi 2958 Gt-Cnrs Aravecchia, Stephanie Georgia Tech Lorraine – UMI 2958 GT-CNRS Geist, Matthieu Université De Lorraine Pradalier, Cedric Georgia Tech Lorraine
Keywords: Recognition, Semantic Scene Understanding, Localization
Abstract: Most of the research effort on image-based place recognition is designed for urban environments. In bucolic environments such as natural scenes with low texture and little semantic content, the main challenge is to handle the variations in visual appearance across time such as illumination, weather, vegetation state or viewpoints. The nature of the variations is different and this leads to a different approach to describing a bucolic scene. We introduce a global image descriptor computed from its semantic and topological information. It is built from the wavelet transforms of the image semantic edges. Matching two images is then equivalent to matching their semantic edge descriptors. We show that this method reaches state-of-the-art image retrieval performance on two multi-season environment-monitoring datasets: the CMU-Seasons and the Symphony Lake dataset. It also generalises to urban scenes on which it is on par with the current baselines NetVLAD and DELF.
Visual Coverage Maintenance for Quadcopters Using Nonsmooth Barrier Functions
Funada, Riku The University of Texas at Austin Santos, María Georgia Institute of Technology Gencho, Takuma Tokyo Institute of Technology Yamauchi, Junya Tokyo Institute of Technology Fujita, Masayuki Tokyo Institute of Technology Egerstedt, Magnus Georgia Institute of Technology
Keywords: Cooperating Robots, Multi-Robot Systems, Sensor Networks
Abstract: This paper presents a coverage control algorithm for teams of quadcopters with downward facing visual sensors that prevents the appearance of coverage holes in-between the monitored areas while maximizing the coverage quality as much as possible. We derive necessary and sufficient conditions for preventing the appearance of holes in-between the fields of views among trios of robots. Because this condition can be expressed as logically combined constraints, control nonsmooth barrier functions are implemented to enforce it. An algorithm which extends control nonsmooth barrier functions to hybrid systems is implemented to manage the switching among barrier functions caused by the changes of the robots composing trio. The performance and validity of the proposed algorithm are evaluated in simulation as well as on a team of quadcopters.
Aggressive Perception-Aware Navigation Using Deep Optical Flow Dynamics and PixelMPC
Lee, Keuntaek Georgia Institute of Technology Gibson, Jason Georgia Institute of Technology Theodorou, Evangelos Georgia Institute of Technology
Keywords: Visual-Based Navigation, Visual Servoing, Visual Tracking
Abstract: Recently, vision-based control has gained traction by leveraging the power of machine learning. In this work, we couple a model predictive control (MPC) framework to a visual pipeline. We introduce deep optical flow (DOF) dynamics, which is a combination of optical flow and robot dynamics. Using the DOF dynamics, MPC explicitly incorporates the predicted movement of relevant pixels into the planned trajectory of a robot. Our implementation of DOF is memory-efficient, data-efficient, and computationally cheap so that it can be computed in real-time for use in an MPC framework. The suggested Pixel Model Predictive Control (PixelMPC) algorithm controls the robot to accomplish a high-speed racing task while maintaining visibility of the important features (gates). This improves the reliability of vision-based estimators for localization and can eventually lead to safe autonomous flight. The proposed algorithm is tested in a photorealistic simulation with a high-speed drone racing task.
Extending Riemmanian Motion Policies to a Class of Underactuated Wheeled-Inverted-Pendulum Robots
Wingo, Bruce Georgia Institute of Technology Cheng, Ching-an Georgia Institute of Technology Murtaza, Muhammad Ali Georgia Institute of Technology Zafar, Munzir Georgia Institute of Technology Hutchinson, Seth Georgia Institute of Technology
Keywords: Underactuated Robots, Motion and Path Planning, Manipulation Planning
Abstract: Riemannian Motion Policies (RMPs) have recently been introduced as a way to specify motion policies for robot tasks in terms of a set of second order differential equations defined directly in the task space. RMP-based approaches have the advantage of being significantly more general than traditional operational space approaches; for example, when using RMPs, generalized task inertia can be fully state-dependent (rather than merely configuration dependent), leading to more effective motions that naturally incorporate the task dynamics, as well as task constraints such as collision avoidance. Until now, RMPs have been applied only to fully actuated systems, i.e., systems for which each degree of freedom (DoF) can be directly actuated by a control input. In this paper, we present a method that generalizes the RMP formalism to a class of underacutated systems whose dynamics are amenable to a particular class of decomposition such that the original underactuated dynamics can be effectively controlled by a fully actuated subsystem. We show the efficacy of the approach by constructing a suitable decomposition for a Wheeled Inverted Pendulum (WIP) humanoid robot, and applying our method to derive motion policies for combined locomotion and manipulation tasks. Simulation results are presented for a 7-DoF system with one degree of underactuation.
Bayesian Learning-Based Adaptive Control for Safety Critical Systems
Fan, David D Georgia Institute of Technology Nguyen, Jennifer West Virginia University Thakker, Rohan Nasa’s Jet Propulsion Laboratory, Caltech Alatur, Nikhilesh Athresh ETH Zurich gha-mohammadi, Ali-akbar NASA-JPL, Caltech Theodorou, Evangelos Georgia Institute of Technology
Keywords: Robust/Adaptive Control of Systems, Robot Safety, Probability and Statistical Methods
Abstract: Deep learning has enjoyed much recent success, and applying state-of-the-art model learning methods to controls is an exciting prospect. However, there is a strong reluctance to use these methods on safety-critical systems, which have constraints on safety, stability, and real-time performance. We propose a framework which satisfies these constraints while allowing the use of deep neural networks for learning model uncertainties. Central to our method is the use of Bayesian model learning, which provides an avenue for maintaining appropriate degrees of caution in the face of the unknown. In the proposed approach, we develop an adaptive control framework leveraging the theory of stochastic CLFs (Control Lyapunov Functions) and stochastic CBFs (Control Barrier Functions) along with tractable Bayesian model learning via Gaussian Processes or Bayesian neural networks. Under reasonable assumptions, we guarantee stability and safety while adapting to unknown dynamics with probability 1. We demonstrate this architecture for high-speed terrestrial mobility targeting potential applications in safety-critical high-speed Mars rover missions.
Learning a Control Policy for Fall Prevention on an Assistive Walking Device
C V Kumar, Visak Georgia Institute of Technology Ha, Sehoon Google Brain Sawicki, Gregory Georgia Institute of Technology Liu, Karen Georgia Tech
Keywords: Wearable Robots, Deep Learning in Robotics and Automation, Physically Assistive Devices
Abstract: Fall prevention is one of the most important components in senior care. We present a technique to augment an assistive walking device with the ability to prevent falls. Given an existing walking device, our method develops a fall predictor and a recovery policy by utilizing the onboard sensors and actuators. The key component of our method is a robust human walking policy that models realistic human gait under a moderate level of perturbations. We use this human walking policy to provide training data for the fall predictor, as well as to teach the recovery policy how to best modify the person’s gait when a fall is imminent. Our evaluation shows that the human walking policy generates walking sequences similar to those reported in biomechanics literature. Our experiments in simulation show that the augmented assistive device can indeed help recover balance from a variety of external perturbations. We also provide a quantitative method to evaluate the design choices for an assistive device.
Soft Pneumatic System for Interface Pressure Regulation and Automated Hands-Free Donning in Robotic Prostheses
Ambrose, Alexander Georgia Institute of Technology Hammond III, Frank L. Georgia Institute of Technology
Keywords: Wearable Robots, Prosthetics and Exoskeletons, Soft Robot Applications
Abstract: This paper discusses the design and preliminary evaluation of a soft pneumatic socket (SPS) with real-time pressure regulation and an automated underactuated donning mechanism (UDM). The ability to modulate the pressure at the human-socket interface of a prosthesis or wearable device to accommodate user’s activities has the potential to make the user more comfortable. Furthermore, a hands-free, underactuated donning mechanism designed to reliably and safely don the socket onto the user may increase the convenience of prostheses and wearable devices. The pneumatic socket and donning mechanism are evaluated on synthetic forearm model designed to closely match the mechanical properties of the human forearm. The pneumatic socket was tested to determine the maximum loads it can withstand before slipping and the displacement of the socket after loading. The donning mechanism was able to successfully don the socket on to the replica forearm with a 100% success rate for the 30 trials that were tested. Both devices were also tested to determine the pressures they impart on the user. The highest pressures the socket can impart on the user is 4psi and the maximum pressure the donning mechanism imparts on the user is 0.83psi. These pressures were found to be lower than the reported pressures that cause pain and tissue damage.
Enhancing Game-Theoretic Autonomous Car Racing Using Control Barrier Functions
Notomista, Gennaro Georgia Institute of Technology Wang, Mingyu Stanford University Schwager, Mac Stanford University Egerstedt, Magnus Georgia Institute of Technology
Keywords: Autonomous Vehicle Navigation, Path Planning for Multiple Mobile Robots or Agents, Multi-Robot Systems
Abstract: In this paper, we consider a two-player racing game, where an autonomous ego vehicle has to be controlled to race against an opponent vehicle, which is either autonomous or human-driven. The approach to control the ego vehicle is based on a Sensitivity-ENhanced NAsh equilibrium seeking (SENNA) method, which uses an iterated best response algorithm in order to optimize for a trajectory in a two-car racing game. This method exploits the interactions between the ego and the opponent vehicle that take place through a collision avoidance constraint. This game-theoretic control method hinges on the ego vehicle having an accurate model and correct knowledge of the state of the opponent vehicle. However, when an accurate model for the opponent vehicle is not available, or the estimation of its state is corrupted by noise, the performance of the approach might be compromised. For this reason, we augment the SENNA algorithm by enforcing Permissive RObust SafeTy (PROST) conditions using control barrier functions. The objective is to successfully overtake or to remain in the front of the opponent vehicle, even when the information about the latter is not fully available. The successful synergy between SENNA and PROST—antithetical to the notable rivalry between the two namesake Formula 1 drivers—is demonstrated through extensive simulated experiments.
MAMS-A*: Multi-Agent Multi-Scale A*
Lim, Jaein Georgia Institute of Technology Tsiotras, Panagiotis Georgia Tech
Keywords: Multi-Robot Systems, Motion and Path Planning
Abstract: We present a multi-scale forward search algorithm for distributed agents to solve single-query shortest path planning problems. Each agent first builds a representation of its own search space of the common environment as a multi-resolution graph, it communicates with the other agents the result of its local search, and it uses received information from other agents to refine its own graph and update the local inconsistency conditions. As a result, all agents attain a common subgraph that includes a provably optimal path in the most informative graph available among all agents, if one exists, without necessarily communicating the entire graph. We prove the completeness and optimality of the proposed algorithm, and present numerical results supporting the advantages of the proposed approach.
Controller Synthesis for Infinitesimally Shape-Similar Formations
Buckley, Ian Georgia Institute of Technology Egerstedt, Magnus Georgia Institute of Technology
Keywords: Multi-Robot Systems, Networked Robots
Abstract: The interplay between network topology and the interaction modalities of a multi-robot team fundamentally impact the types of formations that can be achieved. To explore the trade-offs between network structure and the sensing and communication capabilities of individual robots, this paper applies controller synthesis to formation control of infinitesimally shape-similar frameworks, for which maintaining the relative angles between robots ensures invariance of the framework to translation, rotation, and uniform scaling. Beginning with the development of a controller for the sole purpose of maintaining the formation, the controller-synthesis approach is introduced as a mechanism for incorporating user-designated objectives while ensuring that the formation is maintained. Both centralized and decentralized formulations of the synthesized controller are presented, the resulting sensing and communication requirements are discussed, and the method is demonstrated on a team of differential-drive robots.
UNO: Uncertainty-Aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation
Tian, Junjiao Georgia Institute of Technology Cheung, Wesley Georgia Institute of Technology Glaser, Nathaniel Georgia Institute of Technology Liu, Yen-Cheng Georgia Tech Kira, Zsolt Georgia Institute of Technology
Keywords: Sensor Fusion, RGB-D Perception, Semantic Scene Understanding
Abstract: The fusion of multiple sensor modalities, especially through deep learning architectures, has been an active area of study. However, an under-explored aspect of such work is whether the methods can be robust to degradation across their input modalities, especially when they must generalize to degradation not seen during training. In this work, we propose an uncertainty-aware fusion scheme to effectively fuse inputs that might suffer from a range of known and unknown degradation. Specifically, we analyze a number of uncertainty measures, each of which captures a different aspect of uncertainty, and we propose a novel way to fuse degraded inputs by scaling modality-specific output softmax probabilities. We additionally propose a novel data-dependent spatial temperature scaling method to complement these existing uncertainty measures. Finally, we integrate the uncertainty-scaled output from each modality using a probabilistic noisy-or fusion method. In a photo-realistic simulation environment (AirSim), we show that our method achieves significantly better results on a semantic segmentation task, as compared to state-of-art fusion architectures, on a range of degradation (e.g. fog, snow, frost, and various other types of noise), some of which are unknown during training.
Learning Fast Adaptation with Meta Strategy Optimization
Yu, Wenhao Georgia Institute of Technology Tan, Jie Google Bai, Yunfei Google X Coumans, Erwin Google Inc Ha, Sehoon Google Brain
Keywords: Deep Learning in Robotics and Automation, Learning and Adaptive Systems, Legged Robots
Abstract: The ability to walk in new scenarios is a key milestone on the path toward real-world applications of legged robots. In this work, we introduce Meta Strategy Optimization, a meta-learning algorithm for training policies with latent variable inputs that can quickly adapt to new scenarios with a handful of trials in the target environment. The key idea behind MSO is to expose the same adaptation process, Strategy Optimization (SO), to both the training and testing phases. This allows MSO to effectively learn locomotion skills as well as a latent space that is suitable for fast adaptation. We evaluate our method on a real quadruped robot and demonstrate successful adaptation in various scenarios, including sim-to-real transfer, walking with a weakened motor, or climbing up a slope. Furthermore, we quantitatively analyze the generalization capability of the trained policy in simulated environments. Both real and simulated experiments show that our method outperforms previous methods in adaptation to novel tasks.
Identification of Compliant Contact Parameters and Admittance Force Modulation on a Non-Stationary Compliant Surface
Wijayarathne, Lasitha Georgia Institute of Technology Hammond III, Frank L. Georgia Institute of Technology
Keywords: Force Control, Robust/Adaptive Control of Robotic Systems, Motion Control of Manipulators
Abstract: Although autonomous control of robotic manipulators has been studied for several decades, they are not commonly used in safety-critical applications due to lack of safety and performance guarantees – many of them concerning the modulation of interaction forces. This paper presents a mechanical probing strategy for estimating the environmental impedance parameters of compliant environments, independent a manipulator’s controller design and configuration. The parameter estimates are used in a position-based adaptive force controller to enable control of interaction forces in compliant, stationary and non-stationary environments. This approach is targeted for applications where the workspace is constrained and non-stationary, and where force control is critical to task success. These applications include surgical tasks involving manipulation of compliant, delicate, moving tissues. Results show fast parameter estimation and successful force modulation that compensates for motion.
Who2com: Collaborative Perception Via Learnable Handshake Communication
Liu, Yen-Cheng Georgia Tech Tian, Junjiao Georgia Institute of Technology Ma, Chih-Yao Georgia Tech Glaser, Nathaniel Georgia Institute of Technology Kuo, Chia-Wen Georgia Institute of Technology Kira, Zsolt Georgia Institute of Technology
Keywords: Semantic Scene Understanding, Object Detection, Segmentation and Categorization, Networked Robots
Abstract: In this paper, we propose the problem of collaborative perception, where robots can combine their local observations with those of neighboring agents in a learnable way to improve accuracy on a perception task. Unlike existing work in robotics and multi-agent reinforcement learning, we formulate the problem as one where learned information must be shared across a set of agents in a bandwidth-sensitive manner to optimize for scene understanding tasks such as semantic segmentation. Inspired by networking communication protocols, we propose a handshake communication mechanism where the neural network can learn to compress relevant information needed for each stage. Specifically, a target agent with degraded sensor data sends a compressed request, the other agents respond with matching scores, and the target agent determines who to connect with(i.e., receive information from). We additionally develop the dataset and metrics based on the AirSim simulator where a group of aerial robots perform navigation and search missions over diverse landscapes, such as roads, grasslands, buildings, lakes, etc. We show that for the semantic segmentation task, our handshake communication method significantly improves accuracy by approximately 20% over decentralized baselines, and is comparable to centralized ones using a quarter of the bandwidth.
Enhancing Privacy in Robotics Via Judicious Sensor Selection
Eick, Stephen Georgia Institute of Technology Antón, Annie Georgia Institute of Technology
Keywords: Ethics and Philosophy, Robot Safety
Abstract: Roboticists are grappling with how to address privacy in robot design at a time when regulatory frameworks around the world increasingly require systems to be engineered to preserve and protect privacy. This paper surveys the top robotics journals and conferences over the past four decades to identify contributions with respect to privacy in robot design. Our survey revealed that less than half of one percent of the ~89,120 papers in our study even mention the word privacy. Herein, we propose privacy preserving approaches for roboticists to employ in robot design, including, assessing a robot’s purpose and environment; ensuring privacy by design by selecting sensors that do not collect information that is not essential to the core objectives of that robot; embracing both privacy and performance as fundamental design challenges to be addressed early in the robot lifecycle; and performing privacy impact assessments.
Learning to Collaborate from Simulation for Robot-Assisted Dressing
Clegg, Alexander Georgia Institute of Technology Erickson, Zackory Georgia Institute of Technology Grady, Patrick Georgia Institute of Technology Turk, Greg Georgia Institute of Technology Kemp, Charlie Georgia Institute of Technology Liu, Karen Georgia Tech
Keywords: Simulation and Animation, Deep Learning in Robotics and Automation, Physically Assistive Devices
Abstract: We investigated the application of haptic feedback control and deep reinforcement learning (DRL) to robot-assisted dressing. Our method uses DRL to simultaneously train human and robot control policies as separate neural networks using physics simulations. In addition, we modeled variations in human impairments relevant to dressing, including unilateral muscle weakness, involuntary arm motion, and limited range of motion. Our approach resulted in control policies that successfully collaborate in a variety of simulated dressing tasks involving a hospital gown and a T-shirt. In addition, our approach resulted in policies trained in simulation that enabled a real PR2 robot to dress the arm of a humanoid robot with a hospital gown. We found that training policies for specific impairments dramatically improved performance; that controller execution speed could be scaled after training to reduce the robot’s speed without steep reductions in performance; that curriculum learning could be used to lower applied forces; and that multi-modal sensing, including a simulated capacitive sensor, improved performance.
Koopman Operator Method for Chance-Constrained Motion Primitive Planning
Gutow, Geordan Georgia Institute of Technology Rogers, Jonathan Georgia Institute of Technology
Keywords: Motion and Path Planning, Collision Avoidance, Probability and Statistical Methods
Abstract: The use of motion primitives to plan trajectories has received significant attention in the robotics literature. This work considers the application of motion primitives to path planning and obstacle avoidance problems in which the system is subject to significant parametric and/or initial condition uncertainty. In problems involving parametric uncertainty, optimal path planning is achieved by minimizing the expected value of a cost function subject to probabilistic (chance) constraints on vehicle-obstacle collisions. The Koopman operator provides an efficient means to compute expected values for systems under parametric uncertainty. In the context of motion planning, these include both the expected cost function and chance constraints. This work describes a maneuver-based planning method that leverages the Koopman operator to minimize an expected cost while satisfying user-imposed risk tolerances. The developed method is illustrated in two separate examples using a Dubins car model subject to parametric uncertainty in its dynamics or environment. Prediction of constraint violation probability is compared with a Monte Carlo method to demonstrate the advantages of the Koopman-based calculation.
Benchmark for Skill Learning from Demonstration: Impact of User Experience, Task Complexity, and Start Configuration on Performance
Rana, Muhammad Asif Georgia Institute of Technology Chen, Daphne Georgia Institute of Technology Williams, Jacob Georgia Institute of Technology Chu, Vivian Georgia Institute of Technology Ahmadzadeh, S. Reza University of Massachusetts Lowell Chernova, Sonia Georgia Institute of Technology
Keywords: Learning from Demonstration
Abstract: We contribute a study benchmarking the performance of multiple motion-based learning from demonstration approaches. Given the number and diversity of existing methods, it is critical that comprehensive empirical studies be performed comparing the relative strengths of these techniques. In particular, we evaluate four approaches based on properties an end user may desire for real-world tasks. To perform this evaluation, we collected data from nine participants, across four manipulation tasks. The resulting demonstrations were used to train 180 task models and evaluated on 720 task reproductions on a physical robot. Our results detail how i) complexity of the task, ii) the expertise of the human demonstrator, and iii) the starting configuration of the robot affect task performance. The collected dataset of demonstrations, robot executions, and evaluations are publicly available. Research insights and guidelines are also provided to guide future research and deployment choices about these approaches.
Towards FBG-Based Shape Sensing for Micro-Scale and Meso-Scale Continuum Robots with Large Deflection
Chitalia, Yash Georgia Institute of Technology Deaton, Nancy Joanna Georgia Institute of Technology Jeong, Seokhwan Georgia Institute of Technology Rahman, Nahian Georgia Institute of Technology Desai, Jaydev P. Georgia Institute of Technology
Keywords: Medical Robots and Systems, Surgical Robotics: Steerable Catheters/Needles, Mechanism Design
Abstract: Endovascular and endoscopic surgical procedures require micro-scale and meso-scale continuum robotic tools to navigate complex anatomical structures. In numerous studies, fiber Bragg grating (FBG) based shape sensing has been used for measuring the deflection of continuum robots on larger scales, but has proved to be a challenge for micro-scale and meso-scale robots with large deflections. In this paper, we have developed a sensor by mounting an FBG fiber within a micromachined nitinol tube whose neutral axis is shifted to one side due to the machining. This shifting of the neutral axis allows the FBG core to experience compressive strain when the tube bends. The fabrication method of the sensor has been explicitly detailed and the sensor has been tested with two tendon-driven micro-scale and meso-scale continuum robots with outer diameters of 0.41 mm and 1.93 mm respectively. The compact sensor allows repeatable and reliable estimates of the shape of both scales of robots with minimal hysteresis. We propose an analytical model to derive the curvature of the robot joints from FBG fiber strain and a static model that relates joint curvature to the tendon force. Finally, as proof-of-concept, we demonstrate the feasibility of our sensor assembly by combining tendon force feedback and the FBG strain feedback to generate reliable estimates of joint angles for the meso-scale robot.
Multi-Agent Task Allocation Using Cross-Entropy Temporal Logic Optimization
Banks, Christopher Georgia Institute of Technology Wilson, Sean Georgia Institute of Technology Coogan, Samuel Georgia Tech Egerstedt, Magnus Georgia Institute of Technology
Keywords: Multi-Robot Systems, Formal Methods in Robotics and Automation, Aerial Systems: Applications
Abstract: In this paper, we propose a graph-based search method to optimally allocate tasks to a team of robots given a global task specification. In particular, we define these agents as discrete transition systems. In order to allocate tasks to the team of robots, we decompose finite linear temporal logic (LTL) specifications and consider agent specific cost functions. We propose to use the stochastic optimization technique, cross entropy, to optimize over this cost function. The multi-agent task allocation cross-entropy (MTAC-E) algorithm is developed to determine both when it is optimal to switch to a new agent to complete a task and minimize the costs associated with individual agent trajectories. The proposed algorithm is verified in simulation and experimental results are included.
Adaptive Task Allocation for Heterogeneous Multi-Robot Teams with Evolving and Unknown Robot Capabilities
Emam, Yousef Mr Mayya, Siddharth University of Pennsylvania Notomista, Gennaro Georgia Institute of Technology Bohannon, Addison CCDC Army Research Laboratory Egerstedt, Magnus Georgia Institute of Technology
Keywords: Multi-Robot Systems, Networked Robots, Learning and Adaptive Systems
Abstract: For multi-robot teams with heterogeneous capabilities, typical task allocation methods assign tasks to robots based on the suitability of the robots to perform certain tasks as well as the requirements of the task itself. However, in real-world deployments of robot teams, the suitability of a robot might be unknown prior to deployment, or might vary due to changing environmental conditions. This paper presents an adaptive task allocation and task execution framework which allows individual robots to prioritize among tasks while explicitly taking into account their efficacy at performing the tasks—the parameters of which might be unknown before deployment and/or might vary over time. Such a specialization parameter—encoding the effectiveness of a given robot towards a task—is updated on-the-fly, allowing our algorithm to reassign tasks among robots with the aim of executing them. The developed framework requires no explicit model of the changing environment or of the unknown robot capabilities—it only takes into account the progress made by the robots at completing the tasks. Simulations and experiments demonstrate the efficacy of the proposed approach during variations in environmental conditions and when robot capabilities are unknown before deployment.
Multi-Robot Coordination for Estimation and Coverage of Unknown Spatial Fields
Benevento, Alessia University of Salento Santos, María Georgia Institute of Technology Notarstefano, Giuseppe University of Bologna Paynabar, Kamran Georgia Tech Bloch, Matthieu Georgia Institute of Technology Egerstedt, Magnus Georgia Institute of Technology
Keywords: Multi-Robot Systems, Learning and Adaptive Systems, Optimization and Optimal Control
Abstract: We present an algorithm for multi-robot coverage of an initially unknown spatial scalar field characterized by a density function, whereby a team of robots simultaneously estimates and optimizes its coverage of the density function over the domain. The proposed algorithm borrows powerful concepts from Bayesian Optimization with Gaussian Processes that, when combined with control laws to achieve centroidal Voronoi tessellation, give rise to an adaptive sequential sampling method to explore and cover the domain. The crux of the approach is to apply a control law using a surrogate function of the true density function, which is then successively refined as robots gather more samples for estimation. The performance of the algorithm is justified theoretically under slightly idealized assumptions, by demonstrating asymptotic no-regret with respect to the coverage obtained with a known density function. The performance is also evaluated in simulation and on the Robotarium with small teams of robots, confirming the good performance suggested by the theoretical analysis.
MagNet: Discovering Multi-Agent Interaction Dynamics Using Neural Network
Saha, Priyabrata Georgia Institute of Technology Ali, Arslan Georgia Institute of Technology Mudassar, Burhan Georgia Institute of Technology Long, Yun Georgia Institute of Technology Mukhopadhyay, Saibal Georgia Institute of Technology
Keywords: Dynamics, Deep Learning in Robotics and Automation, Learning and Adaptive Systems
Abstract: We present the MagNet, a neural network-based multi-agent interaction model to discover the governing dynamics and predict evolution of a complex multi-agent system from observations. We formulate a multi-agent system as a coupled non-linear network with a generic ordinary differential equation (ODE) based state evolution, and develop a neural network-based realization of its time-discretized model. MagNet is trained to discover the core dynamics of a multi-agent system from observations, and tuned on-line to learn agent-specific parameters of the dynamics to ensure accurate prediction even when physical or relational attributes of agents, or number of agents change. We evaluate MagNet on a point-mass system in two-dimensional space, Kuramoto phase synchronization dynamics and predator-swarm interaction dynamics demonstrating orders of magnitude improvement in prediction accuracy over traditional deep learning models.
Compliant Electromagnetic Actuator Architecture for Soft Robotics
Kohls, Noah Georgia Institute of Technology Dias, Beatriz Georgia Institute of Technology Mensah, Yaw University of Tennessee – Knoxville Ruddy, Bryan P. University of Auckland Mazumdar, Yi Georgia Institute of Technology
Keywords: Soft Robot Materials and Design, Flexible Robots, Soft Sensors and Actuators
Abstract: Soft materials and compliant actuation concepts have generated new design and control approaches in areas from robotics to wearable devices. Despite the potential of soft robotic systems, most designs currently use hard pumps, valves, and electromagnetic actuators. In this work, we take a step towards fully soft robots by developing a new compliant electromagnetic actuator architecture using gallium-indium liquid metal conductors, as well as compliant permanent magnetic and compliant iron composites. Properties of the new materials are first characterized and then co-fabricated to create an exemplary biologically-inspired soft actuator with pulsing or grasping motions, similar to Xenia soft corals. As current is applied to the liquid metal coil, the compliant permanent magnetic tips on passive silicone arms are attracted or repelled. The dynamics of the robotic actuator are characterized using stochastic system identification techniques and then operated at the resonant frequency of 7 Hz to generate high-stroke (> 6 mm) motions.
When Your Robot Breaks: Active Learning During Plant Failure
Schrum, Mariah Georgia Institute of Technology Gombolay, Matthew Georgia Institute of Technology
Keywords: Failure Detection and Recovery, Learning and Adaptive Systems, Model Learning for Control
Abstract: Detecting and adapting to catastrophic failures in robotic systems requires a robot to learn its new dynamics quickly and safely to best accomplish its goals. To address this challenging problem, we propose probabilistically-safe, online learning techniques to infer the altered dynamics of a robot at the moment a failure (e.g., physical damage) occurs. We combine model predictive control and active learning within a chance-constrained optimization framework to safely and efficiently learn the new plant model of the robot. We leverage a neural network for function approximation in learning the latent dynamics of the robot under failure conditions. Our framework generalizes to various damage conditions while being computationally light-weight to advance real-time deployment. We empirically validate within a virtual environment that we can regain control of a severely damaged aircraft in seconds and require only 0.1 seconds to find safe, information-rich trajectories, outperforming state-of-the-art approaches.
Optimization-Based Distributed Flocking Control for Multiple Rigid Bodies
Ibuki, Tatsuya Tokyo Institute of Technology Wilson, Sean Georgia Institute of Technology Yamauchi, Junya Tokyo Institute of Technology Fujita, Masayuki Tokyo Institute of Technology Egerstedt, Magnus Georgia Institute of Technology
Keywords: Multi-Robot Systems, Optimization and Optimal Control, Swarms
Abstract: This paper considers distributed flocking control on the Special Euclidean group for networked rigid bodies. The method captures the three flocking rules proposed by Reynolds: cohesion; alignment; and separation. The proposed controller is based only on relative pose (position and attitude) information with respect to neighboring rigid bodies so that it can be implemented in a fully distributed manner using only local sensors. The flocking algorithm is moreover based on pose synchronization methods for the cohesion/alignment rules and achieves safe separation distances through the application of control barrier functions. The control input for each rigid body is chosen by solving a distributed optimization problem with constraints for pose synchronization and collision avoidance. Here, the inherent conflict between cohesion and separation is explicitly handled by relaxing the position synchronization constraint. The effectiveness of the proposed flocking algorithm is demonstrated via simulation and hardware experiments.
A Set-Theoretic Approach to Multi-Task Execution and Prioritization
Notomista, Gennaro Georgia Institute of Technology Mayya, Siddharth University of Pennsylvania Selvaggio, Mario Università Degli Studi Di Napoli Federico II Santos, María Georgia Institute of Technology Secchi, Cristian Univ. of Modena & Reggio Emilia
Keywords: Motion Control of Manipulators, Redundant Robots
Abstract: Executing multiple tasks concurrently is important in many robotic applications. Moreover, the prioritization of tasks is essential in applications where safety-critical tasks need to precede application-related objectives, in order to protect both the robot from its surroundings and vice versa. Furthermore, the possibility of switching the priority of tasks during their execution gives the robotic system the flexibility of changing its objectives over time. In this paper, we present an optimization-based task execution and prioritization framework that lends itself to the case of time-varying priorities as well as variable number of tasks. We introduce the concept of extended set-based tasks, encode them using control barrier functions, and execute them by means of a constrained-optimization problem, which can be efficiently solved in an online fashion. Finally, we show the application of the proposed approach to the case of a redundant robotic manipulator.
Assistive Gym: A Physics Simulation Framework for Assistive Robotics
Erickson, Zackory Georgia Institute of Technology Gangaram, Vamsee Georgia Institute of Technology Kapusta, Ariel Georgia Institute of Technology Liu, Karen Georgia Tech Kemp, Charlie Georgia Institute of Technology
Keywords: Physical Human-Robot Interaction, Simulation and Animation, Physically Assistive Devices
Abstract: Autonomous robots have the potential to serve as versatile caregivers that improve quality of life for millions of people worldwide. Yet, conducting research in this area presents numerous challenges, including the risks of physical interaction between people and robots. Physics simulations have been used to optimize and train robots for physical assistance, but have typically focused on a single task. In this paper, we present Assistive Gym, an open source physics simulation framework for assistive robots that models multiple tasks. It includes six simulated environments in which a robotic manipulator can attempt to assist a person with activities of daily living (ADLs): itch scratching, drinking, feeding, body manipulation, dressing, and bathing. Assistive Gym models a person’s physical capabilities and preferences for assistance, which are used to provide a reward function. We present baseline policies trained using reinforcement learning for four different commercial robots in the six environments. We demonstrate that modeling human motion results in better assistance and we compare the performance of different robots. Overall, we show that Assistive Gym is a promising tool for assistive robotics research.
Maneuver at Micro Scale: Steering by Actuation Frequency Control in Micro Bristle Robots
Hao, Zhijian Georgia Institute of Technology Kim, DeaGyu Georgia Institute of Technology Mohazab, Ali Reza Foundation for the Advancement of Sciences, Humanities, Enginee Ansari, Azadeh Georgia Institute of Technology
Keywords: Micro/Nano Robots, Mechanism Design, Automation at Micro-Nano Scales
Abstract: This paper presents a novel steering mechanism, which leads to frequency-controlled locomotion demonstrated for the first time in micro bristle robots. The miniaturized robots are 3D-printed, 12 mm × 8 mm × 6 mm in size, with bristle feature sizes down to 400 μm. The robots can be steered by utilizing the distinct resonance behaviors of the asymmetrical bristle sets. The left and right sets of the bristles have different diameters, and thus different stiffnesses and resonant frequencies. The unique response of each bristle side to the vertical vibrations of a single on-board piezoelectric actuator causes differential steering of the robot. The robot can be modeled as two coupled uniform bristle robots, representing the left and the right sides. At distinct frequencies, the robots can move in all four principal directions: forward, backward, left and right. Furthermore, the full 360° 2D plane can be covered by superimposing the principal actuation frequency components with desired amplitudes. In addition to miniaturized robots, the presented resonance-based steering mechanism can be applied over multiple scales and to other mechanical systems.
Using Synthetic Data and Deep Networks to Recognize Primitive Shapes for Object Grasping
Tang, Chao Georgia Institute of Technology Lin, Yunzhi Georgia Institute of Technology Chu, Fu-Jen University of Michigan Vela, Patricio Georgia Institute of Technology
Keywords: Perception for Grasping and Manipulation, Grasping, Deep Learning in Robotics and Automation
Abstract: A segmentation-based architecture is proposed to decompose objects into multiple primitive shapes from monocular depth input for robotic manipulation. The backbone deep network is trained on synthetic data with 6 classes of primitive shapes generated by a simulation engine. Each primitive shape is designed with parametrized grasp families, permitting the pipeline to identify multiple grasp candidates per shape primitive region. The grasps are priority ordered via proposed ranking algorithm, with the first feasible one chosen for execution. On task-free grasping of individual objects, the method achieves a 94% success rate. On task-oriented grasping, it achieves a 76% success rate.
Barrier-Certified Adaptive Reinforcement Learning with Applications to Brushbot Navigation (I)
Ohnishi, Motoya Paul G. Allen School of Computer Science & Engineering Wang, Li Georgia Institute of Technology Notomista, Gennaro Georgia Institute of Technology Egerstedt, Magnus Georgia Institute of Technology
Keywords: Learning and Adaptive Systems, Robot Safety, Model Learning for Control
Abstract: This paper presents a safe learning framework that employs an adaptive model learning algorithm together with barrier certificates for systems with possibly nonstationary agent dynamics. To extract the dynamic structure of the model, we use a sparse optimization technique. We use the learned model in combination with control barrier certificates that constrain policies (feedback controllers) in order to maintain safety, which refers to avoiding particular undesirable regions of the state space. Under certain conditions, recovery of safety in the sense of Lyapunov stability after violations of safety due to the nonstationarity is guaranteed. In addition, we reformulate an action-value function approximation to make any kernel-based nonlinear function estimation method applicable to our adaptive learning framework. Lastly, solutions to the barrier-certified policy optimization are guaranteed to be globally optimal, ensuring the greedy policy improvement under mild conditions. The resulting framework is validated via simulations of a quadrotor, which has previously been used under stationarity assumptions in the safe learnings literature, and is then tested on a real robot, the brushbot, whose dynamics is unknown, highly complex, and nonstationary.
Patient-Specific, Voice-Controlled, Robotic FLEXotendon Glove-II System for Spinal Cord Injury
Tran, Phillip Georgia Institute of Technology Jeong, Seokhwan Georgia Institute of Technology Wolf, Steven Emory University School of Medicine Desai, Jaydev P. Georgia Institute of Technology
Keywords: Rehabilitation Robotics, Medical Robots and Systems, Soft Robot Applications
Abstract: Reduced hand function in spinal cord injury (SCI) patients is commonly associated with a lower quality of life and limits the autonomy of the patient because he/she cannot perform most tasks independently. Robotic rehabilitation exoskeletons have been introduced as a method for assisting in hand function restoration. In this work, we propose a voice-controlled, tendon-actuated soft exoskeleton for improving hand function rehabilitation. The exoskeleton is constructed from soft materials to conform to the user’s hand for improved fit and flexibility. A partially biomimetic tendon routing strategy independently actuates the index finger, middle finger, and thumb for a total of 4 degrees-of-freedom of the overall system. Nitinol wires are used for passive finger extension and screw-guided twisted tendon actuators are used for active finger flexion to create a compact, lightweight actuation mechanism. A continuous voice control strategy is implemented to provide a hands-free control interface and a simplified user interface experience while retaining distinct user intention. The exoskeleton was evaluated in a case study with a spinal cord injury patient. The patient used the exoskeleton and completed range-of-motion measurement as well as hand function tests, including the Box and Block Test and Jebsen-Taylor Hand Function Test.
Integration of Self-Sealing Suction Cups on the FLEXotendon Glove-II Robotic Exoskeleton System
Jeong, Seokhwan Georgia Institute of Technology Tran, Phillip Georgia Institute of Technology Desai, Jaydev P. Georgia Institute of Technology
Keywords: Rehabilitation Robotics, Medical Robots and Systems, Soft Robot Applications
Abstract: This paper presents a hand exoskeleton using self-sealing suction cup modules to assist and simplify various grasping tasks. Robotic hands, grippers, and hand rehabilitation exoskeletons require complex motion planning and control algorithms to manipulate various objects, which increases system complexity. The proposed hand exoskeleton integrated with self-sealing suction cup modules provides simplified grasping with the assistance of suction. The suction cup has a self-sealing mechanism with a passive opening valve and it reduces vacuum consumption and pump noise. The gimbal mechanism allows the suction cup to have a wide range of contact angles, which increases adaptability of grasping of the exoskeleton. The fabrication process of the device is introduced with the suction cup design and material selection. The vacuum canister and solenoid valve that comprise the proposed pneumatic circuit provide a continuous vacuum supply source without continuous operation of a vacuum pump and autonomous suction/release motion, respectively. The performance of the hand exoskeleton was demonstrated with various grasping tasks and it provided stable grasping and pick-and-place task without complex finger manipulation. The proposed hand exoskeleton has the potential to simplify the grasping process and allow patients with hand dysfunction to expand their versatility of grasping tasks.
Magnetic Milli-Robot Swarm Platform: A Safety Barrier Certificate Enabled, Low-Cost Test Bed
Hsu, Allen SRI International Huihua, Zhao Georgia Institute of Technology Gaudreault, Martin SRI International Wong-Foy, Annjoe SRI International Pelrine, Ron SRI International
Keywords: Micro/Nano Robots, Multi-Robot Systems, Swarms
Abstract: Swarms of micro- and milli-sized robots have the potential to advance biological micro-manipulation, micro-assembly and manufacturing, and provide an ideal platform for studying large swarm behaviors and control. Due to their small size and low cost, tens to hundreds of micro/milli robots can function in parallel to perform a task that otherwise would be too cumbersome or costly for a larger macroscopic robot. Here, we demonstrate a scalable system and modular circuit architecture for controlling and coordinating the motion of >10’s of magnetic micro/milli robots. By modifying the concepts of safety barrier certificates to our magnetic robot hardware, we achieve minimally invasive, collision-free, 2D position control (x,y) of up to N = 16 robots in a low-cost tabletop (288mm x 288mm) magnetic milli-robot platform with up to 288 degrees of freedom. We show that the introduction of random dithering can achieve a 100% success rate (i.e., no deadlocking), enabling the system to serve as a platform for the study of various swarm-like behaviors or multi-agent robotic coordination.