Correcting Robot Plans with Natural Language Feedback

• URL: http://arxiv.org/abs/2204.05186v1
• Date: Mon, 11 Apr 2022 15:22:43 GMT
• Title: Correcting Robot Plans with Natural Language Feedback
• Authors: Pratyusha Sharma, Balakumar Sundaralingam, Valts Blukis, Chris Paxton, Tucker Hermans, Antonio Torralba, Jacob Andreas, Dieter Fox
• Abstract summary: We explore natural language as an expressive and flexible tool for robot correction. We show that these transformations enable users to correct goals, update robot motions, and recover from planning errors. Our method makes it possible to compose multiple constraints and generalizes to unseen scenes, objects, and sentences in simulated environments and real-world environments.
• Score: 88.92824527743105
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When humans design cost or goal specifications for robots, they often produce specifications that are ambiguous, underspecified, or beyond planners' ability to solve. In these cases, corrections provide a valuable tool for human-in-the-loop robot control. Corrections might take the form of new goal specifications, new constraints (e.g. to avoid specific objects), or hints for planning algorithms (e.g. to visit specific waypoints). Existing correction methods (e.g. using a joystick or direct manipulation of an end effector) require full teleoperation or real-time interaction. In this paper, we explore natural language as an expressive and flexible tool for robot correction. We describe how to map from natural language sentences to transformations of cost functions. We show that these transformations enable users to correct goals, update robot motions to accommodate additional user preferences, and recover from planning errors. These corrections can be leveraged to get 81% and 93% success rates on tasks where the original planner failed, with either one or two language corrections. Our method makes it possible to compose multiple constraints and generalizes to unseen scenes, objects, and sentences in simulated environments and real-world environments.

Related papers

• Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation [65.46610405509338]
  We seek to learn a generalizable goal-conditioned policy that enables zero-shot robot manipulation. Our framework,Track2Act predicts tracks of how points in an image should move in future time-steps based on a goal. We show that this approach of combining scalably learned track prediction with a residual policy enables diverse generalizable robot manipulation.
  arXiv  Detail & Related papers  (2024-05-02T17:56:55Z)
• Yell At Your Robot: Improving On-the-Fly from Language Corrections [84.09578841663195]
  We show that high-level policies can be readily supervised with human feedback in the form of language corrections. This framework enables robots not only to rapidly adapt to real-time language feedback, but also incorporate this feedback into an iterative training scheme.
  arXiv  Detail & Related papers  (2024-03-19T17:08:24Z)
• Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans [58.27029676638521]
  We show how passive human videos can serve as a rich source of data for learning such generalist robots. We learn a human plan predictor that, given a current image of a scene and a goal image, predicts the future hand and object configurations. We show that our learned system can perform over 16 manipulation skills that generalize to 40 objects.
  arXiv  Detail & Related papers  (2023-12-01T18:54:12Z)
• simPLE: a visuotactile method learned in simulation to precisely pick, localize, regrasp, and place objects [16.178331266949293]
  This paper explores solutions for precise and general pick-and-place. We propose simPLE as a solution to precise pick-and-place. SimPLE learns to pick, regrasp and place objects precisely, given only the object CAD model and no prior experience.
  arXiv  Detail & Related papers  (2023-07-24T21:22:58Z)
• "No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy [70.45420918526926]
  We present LILAC, a framework for incorporating and adapting to natural language corrections online during execution. Instead of discrete turn-taking between a human and robot, LILAC splits agency between the human and robot. We show that our corrections-aware approach obtains higher task completion rates, and is subjectively preferred by users.
  arXiv  Detail & Related papers  (2023-01-06T15:03:27Z)
• LaTTe: Language Trajectory TransformEr [33.7939079214046]
  This work proposes a flexible language-based framework to modify generic 3D robotic trajectories. We employ an auto-regressive transformer to map natural language inputs and contextual images into changes in 3D trajectories. We show through simulations and real-life experiments that the model can successfully follow human intent.
  arXiv  Detail & Related papers  (2022-08-04T22:43:21Z)
• Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation [80.29069988090912]
  We study the problem of learning a range of vision-based manipulation tasks from a large offline dataset of robot interaction. We propose to leverage offline robot datasets with crowd-sourced natural language labels. We find that our approach outperforms both goal-image specifications and language conditioned imitation techniques by more than 25%.
  arXiv  Detail & Related papers  (2021-09-02T17:42:13Z)
• Composing Pick-and-Place Tasks By Grounding Language [41.075844857146805]
  We present a robot system that follows unconstrained language instructions to pick and place arbitrary objects. Our approach infers objects and their relationships from input images and language expressions. Results obtained using a real-world PR2 robot demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2021-02-16T11:29:09Z)
• Learning from Incremental Directional Corrections [9.45570271906093]
  We propose a technique which enables a robot to learn a control objective function incrementally from human user's corrections. We only assume that each of the human's corrections, regardless of its magnitude, points in a direction that improves the robot's current motion. The proposed method uses the direction of a correction to update the estimate of the objective function based on a cutting plane technique.
  arXiv  Detail & Related papers  (2020-11-30T17:16:39Z)

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.