A Framework for Learning from Demonstration with Minimal Human Effort

• URL: http://arxiv.org/abs/2306.09211v1
• Date: Thu, 15 Jun 2023 15:49:37 GMT
• Title: A Framework for Learning from Demonstration with Minimal Human Effort
• Authors: Marc Rigter, Bruno Lacerda, Nick Hawes
• Abstract summary: We consider robot learning in the context of shared autonomy, where control of the system can switch between a human teleoperator and autonomous control. In this setting we address reinforcement learning, and learning from demonstration, where there is a cost associated with human time. We show that our approach to controller selection reduces the human cost to perform two simulated tasks and a single real-world task.
• Score: 11.183124892686239
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider robot learning in the context of shared autonomy, where control of the system can switch between a human teleoperator and autonomous control. In this setting we address reinforcement learning, and learning from demonstration, where there is a cost associated with human time. This cost represents the human time required to teleoperate the robot, or recover the robot from failures. For each episode, the agent must choose between requesting human teleoperation, or using one of its autonomous controllers. In our approach, we learn to predict the success probability for each controller, given the initial state of an episode. This is used in a contextual multi-armed bandit algorithm to choose the controller for the episode. A controller is learnt online from demonstrations and reinforcement learning so that autonomous performance improves, and the system becomes less reliant on the teleoperator with more experience. We show that our approach to controller selection reduces the human cost to perform two simulated tasks and a single real-world task.

Related papers

• Zero-Cost Whole-Body Teleoperation for Mobile Manipulation [8.71539730969424]
  MoMa-Teleop is a novel teleoperation method that delegates the base motions to a reinforcement learning agent. We demonstrate that our approach results in a significant reduction in task completion time across a variety of robots and tasks.
  arXiv  Detail & Related papers  (2024-09-23T15:09:45Z)
• Unifying 3D Representation and Control of Diverse Robots with a Single Camera [48.279199537720714]
  We introduce Neural Jacobian Fields, an architecture that autonomously learns to model and control robots from vision alone. Our approach achieves accurate closed-loop control and recovers the causal dynamic structure of each robot.
  arXiv  Detail & Related papers  (2024-07-11T17:55:49Z)
• Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition [48.65867987106428]
  We introduce a novel system for joint learning between human operators and robots. It enables human operators to share control of a robot end-effector with a learned assistive agent. It reduces the need for human adaptation while ensuring the collected data is of sufficient quality for downstream tasks.
  arXiv  Detail & Related papers  (2024-06-29T03:37:29Z)
• Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data [101.43350024175157]
  Self-supervised learning has the potential to decrease the amount of human annotation and engineering effort required to learn control strategies. Our work builds on prior work showing that the reinforcement learning (RL) itself can be cast as a self-supervised problem. We demonstrate that a self-supervised RL algorithm based on contrastive learning can solve real-world, image-based robotic manipulation tasks.
  arXiv  Detail & Related papers  (2023-06-06T01:36:56Z)
• Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning [54.636562516974884]
  In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. In this work, we propose MEDAL++, a novel design for self-improving robotic systems. The robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations.
  arXiv  Detail & Related papers  (2023-03-02T18:51:38Z)
• Learning Reward Functions for Robotic Manipulation by Observing Humans [92.30657414416527]
  We use unlabeled videos of humans solving a wide range of manipulation tasks to learn a task-agnostic reward function for robotic manipulation policies. The learned rewards are based on distances to a goal in an embedding space learned using a time-contrastive objective.
  arXiv  Detail & Related papers  (2022-11-16T16:26:48Z)
• GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots [87.32145104894754]
  We introduce a framework for training generalized locomotion (GenLoco) controllers for quadrupedal robots. Our framework synthesizes general-purpose locomotion controllers that can be deployed on a large variety of quadrupedal robots. We show that our models acquire more general control strategies that can be directly transferred to novel simulated and real-world robots.
  arXiv  Detail & Related papers  (2022-09-12T15:14:32Z)
• Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube [24.530131506065164]
  We build a system that enables any human to control a robot hand and arm, simply by demonstrating motions with their own hand. The robot observes the human operator via a single RGB camera and imitates their actions in real-time. We leverage this data to train a system that understands human hands and retargets a human video stream into a robot hand-arm trajectory that is smooth, swift, safe, and semantically similar to the guiding demonstration.
  arXiv  Detail & Related papers  (2022-02-21T18:59:59Z)
• Training Robots without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer [4.318590074766604]
  Deep imitation learning is promising for robot manipulation because it only requires demonstration samples. Existing demonstration methods have deficiencies; bilateral teleoperation requires a complex control scheme and is expensive. This research proposes a new master-to-robot (M2R) policy transfer system that does not require robots for teaching force feedback-based manipulation tasks.
  arXiv  Detail & Related papers  (2022-02-19T10:55:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.