Pith. sign in

REVIEW 5 cited by

Interactive Robot Learning from Verbal Correction

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.17555 v1 pith:II2U22NR submitted 2023-10-26 cs.RO cs.AIcs.LG

classification cs.ROcs.AIcs.LG
keywords robotverbaldesignolafabilitycorrectionslearnlearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The ability to learn and refine behavior after deployment has become ever more important for robots as we design them to operate in unstructured environments like households. In this work, we design a new learning system based on large language model (LLM), OLAF, that allows everyday users to teach a robot using verbal corrections when the robot makes mistakes, e.g., by saying "Stop what you're doing. You should move closer to the cup." A key feature of OLAF is its ability to update the robot's visuomotor neural policy based on the verbal feedback to avoid repeating mistakes in the future. This is in contrast to existing LLM-based robotic systems, which only follow verbal commands or corrections but not learn from them. We demonstrate the efficacy of our design in experiments where a user teaches a robot to perform long-horizon manipulation tasks both in simulation and on physical hardware, achieving on average 20.0% improvement in policy success rate. Videos and more results are at https://ut-austin-rpl.github.io/olaf/

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Effects of Robot Competency and Motion Legibility on Human Correction Feedback

    cs.RO 2025-01 conditional novelty 7.0 of 10

    A user study shows that robot competency and motion legibility shift when and whether people correct a robot, contradicting two common assumptions in learning-from-corrections.

  2. Robix: A Unified Model for Robot Interaction, Reasoning and Planning

    cs.AI 2025-09 conditional novelty 6.0 of 10

    A three-stage-trained VLM unifies robot planning and dialogue, and beats commercial VLMs on the authors' interactive-task benchmarks.

  3. Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework

    cs.LG 2024-11 conditional novelty 6.0 of 10

    A conceptual framework classifies human feedback to RL agents along nine dimensions and seven quality criteria, unifying human-centered, interface-centered, and model-centered design perspectives.

  4. Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

    cs.RO 2025-09 conditional novelty 5.0 of 10

    Ask-to-Clarify combines a dialogue VLM with a frozen diffusion policy so a robot can disambiguate instructions and then execute low-level actions on 8 real-world tasks.

  5. Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent

    cs.RO 2025-08 conditional novelty 5.0 of 10

    A robot replanner that compares scene graphs to successful demonstrations before each subtask, triggering LLM-based replanning on mismatch, raises task success in AI2-THOR.

Pith tools