PATO: Policy Assisted TeleOperation for Scalable Robot Data Collection
- URL: http://arxiv.org/abs/2212.04708v2
- Date: Thu, 1 Jun 2023 22:48:06 GMT
- Title: PATO: Policy Assisted TeleOperation for Scalable Robot Data Collection
- Authors: Shivin Dass, Karl Pertsch, Hejia Zhang, Youngwoon Lee, Joseph J. Lim,
Stefanos Nikolaidis
- Abstract summary: Policy Assisted TeleOperation (PATO) is a system which automates part of the demonstration collection process using a learned assistive policy.
PATO autonomously executes repetitive behaviors in data collection and asks for human input only when it is uncertain about which subtask or behavior to execute.
- Score: 19.04536551595612
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large-scale data is an essential component of machine learning as
demonstrated in recent advances in natural language processing and computer
vision research. However, collecting large-scale robotic data is much more
expensive and slower as each operator can control only a single robot at a
time. To make this costly data collection process efficient and scalable, we
propose Policy Assisted TeleOperation (PATO), a system which automates part of
the demonstration collection process using a learned assistive policy. PATO
autonomously executes repetitive behaviors in data collection and asks for
human input only when it is uncertain about which subtask or behavior to
execute. We conduct teleoperation user studies both with a real robot and a
simulated robot fleet and demonstrate that our assisted teleoperation system
reduces human operators' mental load while improving data collection
efficiency. Further, it enables a single operator to control multiple robots in
parallel, which is a first step towards scalable robotic data collection. For
code and video results, see https://clvrai.com/pato
Related papers
- Open-TeleVision: Teleoperation with Immersive Active Visual Feedback [17.505318269362512]
Open-TeleVision allows operators to actively perceive the robot's surroundings in a stereoscopic manner.
The system mirrors the operator's arm and hand movements on the robot, creating an immersive experience.
We validate the effectiveness of our system by collecting data and training imitation learning policies on four long-horizon, precise tasks.
arXiv Detail & Related papers (2024-07-01T17:55:35Z) - 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) - AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents [109.3804962220498]
AutoRT is a system to scale up the deployment of operational robots in completely unseen scenarios with minimal human supervision.
We demonstrate AutoRT proposing instructions to over 20 robots across multiple buildings and collecting 77k real robot episodes via both teleoperation and autonomous robot policies.
We experimentally show that such "in-the-wild" data collected by AutoRT is significantly more diverse, and that AutoRT's use of LLMs allows for instruction following data collection robots that can align to human preferences.
arXiv Detail & Related papers (2024-01-23T18:45:54Z) - InteRACT: Transformer Models for Human Intent Prediction Conditioned on Robot Actions [7.574421886354134]
InteRACT architecture pre-trains a conditional intent prediction model on large human-human datasets and fine-tunes on a small human-robot dataset.
We evaluate on a set of real-world collaborative human-robot manipulation tasks and show that our conditional model improves over various marginal baselines.
arXiv Detail & Related papers (2023-11-21T19:15:17Z) - Giving Robots a Hand: Learning Generalizable Manipulation with
Eye-in-Hand Human Video Demonstrations [66.47064743686953]
Eye-in-hand cameras have shown promise in enabling greater sample efficiency and generalization in vision-based robotic manipulation.
Videos of humans performing tasks, on the other hand, are much cheaper to collect since they eliminate the need for expertise in robotic teleoperation.
In this work, we augment narrow robotic imitation datasets with broad unlabeled human video demonstrations to greatly enhance the generalization of eye-in-hand visuomotor policies.
arXiv Detail & Related papers (2023-07-12T07:04:53Z) - 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) - From One Hand to Multiple Hands: Imitation Learning for Dexterous
Manipulation from Single-Camera Teleoperation [26.738893736520364]
We introduce a novel single-camera teleoperation system to collect the 3D demonstrations efficiently with only an iPad and a computer.
We construct a customized robot hand for each user in the physical simulator, which is a manipulator resembling the same kinematics structure and shape of the operator's hand.
With imitation learning using our data, we show large improvement over baselines with multiple complex manipulation tasks.
arXiv Detail & Related papers (2022-04-26T17:59:51Z) - Lifelong Robotic Reinforcement Learning by Retaining Experiences [61.79346922421323]
Many multi-task reinforcement learning efforts assume the robot can collect data from all tasks at all times.
In this work, we study a practical sequential multi-task RL problem motivated by the practical constraints of physical robotic systems.
We derive an approach that effectively leverages the data and policies learned for previous tasks to cumulatively grow the robot's skill-set.
arXiv Detail & Related papers (2021-09-19T18:00:51Z) - Learning Predictive Models From Observation and Interaction [137.77887825854768]
Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works.
However, learning a model that captures the dynamics of complex skills represents a major challenge.
We propose a method to augment the training set with observational data of other agents, such as humans.
arXiv Detail & Related papers (2019-12-30T01:10:41Z)
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.