More Like this

1. Learning a Decentralized Multi-arm Motion Planner

   Ha, Huy; Xu, Jingxi; Song, Shuran (November 2020, Proceedings of the 2020 Conference on Robot Learning)

   We present a closed-loop multi-arm motion planner that is scalable and flexible with team size. Traditional multi-arm robotic systems have relied on centralized motion planners, whose run times often scale exponentially with team size, and thus, fail to handle dynamic environments with open-loop control. In this paper, we tackle this problem with multi-agent reinforcement learning, where a shared policy network is trained to control each individual robot arm to reach its target end-effector pose given observations of its workspace state and target end-effector pose. The policy is trained using Soft Actor-Critic with expert demonstrations from a sampling-based motion planning algorithm (i.e., BiRRT). By leveraging classical planning algorithms, we can improve the learning efficiency of the reinforcement learning algorithm while retaining the fast inference time of neural networks. The resulting policy scales sub-linearly and can be deployed on multi-arm systems with variable team sizes. Thanks to the closed-loop and decentralized formulation, our approach generalizes to 5-10 multiarm systems and dynamic moving targets (>90% success rate for a 10-arm system), despite being trained on only 1-4 arm planning tasks with static targets. 

   more » « less
2. A Validated Physical Model For Real-Time Simulation of Soft Robotic Snakes

   Gasoto, Renato; Macklin, Miles; Liu, Xuan; Sun, Yinan; Erleben, Kenny; Onal, Cagdas; Fu, Jie (May 2019, International Conference on Robotics and Automation)

   In this work, we present a framework that is capable of accurately representing soft robotic actuators in a multiphysics environment in real-time. We propose a constraint-based dynamics model of a 1-dimensional pneumatic soft actuator that accounts for internal pressure forces, as well as the effect of actuator latency and damping under inflation and deflation and demonstrate its accuracy a full soft robotic snake with the composition of multiple 1D actuators. We verify our model's accuracy in static deformation and dynamic locomotion open-loop control experiments. To achieve real-time performance we leverage the parallel computation power of GPUs to allow interactive control and feedback. 

   more » « less
3. Minimal activation with maximal reach: Reachability clouds of bio-inspired slender manipulators

   https://doi.org/10.1016/j.eml.2024.102207  

   Kaczmarski, Bartosz; Moulton, Derek E; Goriely, Alain; Kuhl, Ellen (September 2024, Extreme Mechanics Letters)

   In the field of soft robotics, flexibility, adaptability, and functionality define a new era of robotic systems that can safely deform, reach, and grasp. To optimize the design of soft robotic systems, it is critical to understand their configuration space and full range of motion across a wide variety of design parameters. Here we integrate extreme mechanics and soft robotics to provide quantitative insights into the design of bio-inspired soft slender manipulators using the concept of reachability clouds. For a minimal three-actuator design inspired by the elephant trunk, we establish an efficient and robust reduced-order method to generate reachability clouds of almost half a million points each to visualize the accessible workspace of a wide variety of manipulator designs. We generate an atlas of 256 reachability clouds by systematically varying the key design parameters including the fiber count, revolution, tapering angle, and activation magnitude. Our results demonstrate that reachability clouds not only offer an immediately clear perspective into the inverse problem of control, but also introduce powerful metrics to characterize reachable volumes, unreachable regions, and actuator redundancy to quantify the performance of soft slender robots. 

   more » « less
4. Autonomous, Monocular, Vision-Based Snake Robot Navigation and Traversal of Cluttered Environments using Rectilinear Gait Motion

   Chang, A.H.; Feng, S.; Zhao, Y.; Smith, J.S.; Vela, P.A. (August 2019, arXiv)

   Rectilinear forms of snake-like robotic locomotion are anticipated to be an advantage in obstacle-strewn scenarios characterizing urban disaster zones, subterranean collapses, and other natural environments. The elongated, laterally narrow footprint associated with these motion strategies is well suited to traversal of confined spaces and narrow pathways. Navigation and path planning in the absence of global sensing, however, remains a pivotal challenge to be addressed prior to practical deployment of these robotic mechanisms. Several challenges related to visual processing and localization need to be resolved to to enable navigation. As a first pass in this direction, we equip a wireless, monocular color camera to the head of a robotic snake. Visiual odometry and mapping from ORB-SLAM permits self-localization in planar, obstacle strewn environments. Ground plane traversability segmentation in conjunction with perception-space collision detection permits path planning for navigation. A previously presented dynamical reduction of rectilinear snake locomotion to a non-holonomic kinematic vehicle informs both SLAM and planning. The simplified motion model is then applied to track planned trajectories through an obstacle configuration. This navigational framework enables a snake-like robotic platform to autonomously navigate and traverse unknown scenarios with only monocular vision. 

   more » « less
5. Improving the Accuracy of Wearable Sensors for Human Locomotion Tracking Using Phase-Locked Regression Models

   https://doi.org/10.1109/ICORR.2019.8779428  

   Duong, Ton T.; Zhang, Huanghe; Lynch, T. Sean; Zanotto, Damiano (June 2019, 2019 IEEE 16th International Conference on Rehabilitation Robotics (ICORR))

   The trend toward soft wearable robotic systems creates a compelling need for new and reliable sensor systems that do not require a rigid mounting frame. Despite the growing use of inertial measurement units (IMUs) in motion tracking applications, sensor drift and IMU-to-segment misalignment still represent major problems in applications requiring high accuracy. This paper proposes a novel 2-step calibration method which takes advantage of the periodic nature of human locomotion to improve the accuracy of wearable inertial sensors in measuring lower-limb joint angles. Specifically, the method was applied to the determination of the hip joint angles during walking tasks. The accuracy and precision of the calibration method were accessed in a group of N = 8 subjects who walked with a custom-designed inertial motion capture system at 85% and 115% of their comfortable pace, using an optical motion capture system as reference. In light of its low computational complexity and good accuracy, the proposed approach shows promise for embedded applications, including closed-loop control of soft wearable robotic systems. 

   more » « less