ROAICLCVLGApr 11, 2022

Correcting Robot Plans with Natural Language Feedback

MicrosoftMITNVIDIA
arXiv:2204.05186v1124 citationsh-index: 140
Originality Incremental advance
AI Analysis

This addresses the challenge of human-in-the-loop robot control by providing a flexible correction method, though it is incremental as it builds on existing correction techniques.

The paper tackles the problem of ambiguous or underspecified robot plans by using natural language feedback to correct them, achieving 81% and 93% success rates on tasks where the original planner failed with one or two corrections.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes