Robot Behavior Personalization from Sparse User Feedback
Not on the map. Why?
Abstract (arXiv)
As service robots become more general-purpose, they will need to adapt to their users' preferences over a large set of all possible tasks that they can perform. This includes preferences regarding which actions the users prefer to delegate to robots as opposed to doing themselves. Existing personalization approaches require task-specific data for each user. To handle diversity across all household tasks and users, and nuances in user preferences across tasks, we propose to learn a task adaptation function independently, which can be used in tandem with any universal robot policy to customize robot behavior. We create Task Adaptation using Abstract Concepts (TAACo) framework. TAACo can learn to predict the user's preferred manner of assistance with any given task, by mediating reasoning through a representation composed of abstract concepts built based on user feedback. TAACo can generalize to an open set of household tasks from small amount of user feedback and explain its inferences through intuitive concepts. We evaluate our model on a dataset we collected of 5 people's preferences, and show that TAACo outperforms GPT-4 by 16% and a rule-based system by 54%, on prediction accuracy, with 40 samples of user feedback.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 25 Oct 2024.
Builds on
29 of 46 references.
References · 29
- 2023GPT-4 Technical Reportcited by 18,132
- 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
- 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
- 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 459
- 2022VIMA: General Robot Manipulation with Multimodal Promptscited by 403
- 2022Visual Language Maps for Robot Navigationcited by 362
- 2023TidyBot: Personalized Robot Assistance with Large Language Modelscited by 219
- 2022Interactive Language: Talking to Robots in Real Timecited by 217
- 2022Open-vocabulary Queryable Scene Representations for Real World Planningcited by 159
- 2021Consequences of Misaligned AIcited by 79
- 2022Correcting Robot Plans with Natural Language Feedbackcited by 68
- 2023"No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomycited by 60
17 more
- 2020The EMPATHIC Framework for Task Learning from Implicit Human Feedbackcited by 38
- 2023Large Language Models as Zero-Shot Human Models for Human-Robot Interactioncited by 30
- 2020AvE: Assistance via Empowermentcited by 27
- 2021My House, My Rules: Learning Tidying Preferences with Graph Neural Networkscited by 27
- 2024Learning to Learn Faster from Human Feedback with Language Model Predictive Controlcited by 25
- 2022Proactive Robot Assistance via Spatio-Temporal Object Modelingcited by 18
- 2023Concept Learning for Interpretable Multi-Agent Reinforcement Learningcited by 18
- 2023State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understandingcited by 17
- 2023Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptationcited by 16
- 2022Transformers are Adaptable Task Plannerscited by 15
- 2024Verifiably Following Complex Robot Instructions with Foundation Modelscited by 15
- 2022Coordination with Humans via Strategy Matchingcited by 14
- 2023HOI4ABOT: Human-Object Interaction Anticipation for Human Intention Reading Collaborative roBOTscited by 12
- 2023ConSOR: A Context-Aware Semantic Object Rearrangement Framework for Partially Arranged Scenescited by 6
- 2023Predicting Routine Object Usage for Proactive Robot Assistancecited by 5
- 2021Learning What To Do by Simulating the Pastcited by 4
- 2024Explaining Autonomy: Enhancing Human-Robot Interaction through Explanation Generation with Large Language Modelscited by 4
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.