# Enhancing Goal Inference via Correction Timing

arXiv: https://arxiv.org/abs/2602.18603 · HTML: https://mlsanity.com/paper/2602.18603/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 54 references that are in the map.
- First posted on arXiv 20 Feb 2026.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Trial without Error: Towards Safe Reinforcement Learning via Human Intervention](https://mlsanity.com/paper/1707.05173/) (2017)
- [Shared Autonomy via Hindsight Optimization for Teleoperation and Teaming](https://mlsanity.com/paper/1706.00155/) (2017)
- [A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models](https://mlsanity.com/paper/2502.13187/) (2025)
- [Learning Trajectory Preferences for Manipulators via Iterative Improvement](https://mlsanity.com/paper/1306.6294/) (2013)
- [Learning Preferences for Manipulation Tasks from Online Coactive Feedback](https://mlsanity.com/paper/1601.00741/) (2016)
- [The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models](https://mlsanity.com/paper/2204.10759/) (2022)
- [Quantifying Hypothesis Space Misspecification in Learning from Human-Robot Demonstrations and Physical Corrections](https://mlsanity.com/paper/2002.00941/) (2020)
- [Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections](https://mlsanity.com/paper/2107.02349/) (2021)
- [Learning under Misspecified Objective Spaces](https://mlsanity.com/paper/1810.05157/) (2018)
- [What Matters to You? Towards Visual Representation Alignment for Robot Learning](https://mlsanity.com/paper/2310.07932/) (2023)
- [Improving User Specifications for Robot Behavior through Active Preference Learning: Framework and Evaluation](https://mlsanity.com/paper/1907.10412/) (2019)
- [Active Intent Disambiguation for Shared Control Robots](https://mlsanity.com/paper/2005.03652/) (2020)
- [Learning Failure Prevention Skills for Safe Robot Manipulation](https://mlsanity.com/paper/2305.02807/) (2023)
- [Effects of Robot Competency and Motion Legibility on Human Correction Feedback](https://mlsanity.com/paper/2501.03515/) (2025)
- [Model-free Friction Observers for Flexible Joint Robots with Torque Measurements](https://mlsanity.com/paper/1907.00553/) (2019)
- [Anticipatory Human-Robot Collaboration via Multi-Objective Trajectory Optimization](https://mlsanity.com/paper/2006.03614/) (2020)
- [Autonomous Interpretation of Demonstrations for Modification of Dynamical Movement Primitives](https://mlsanity.com/paper/1905.11130/) (2019)
- [Defining Preferred and Natural Robot Motions in Immersive Telepresence from a First-Person Perspective](https://mlsanity.com/paper/2102.12719/) (2021)

## Built on by (most cited first, 1 of 1)

- [Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Collaboration](https://mlsanity.com/paper/2609.13982/) (2026)

## Abstract (arXiv)

Corrections offer a natural modality for people to provide feedback to a robot, by (i) intervening in the robot's behavior when they believe the robot is failing (or will fail) the task objectives and (ii) modifying the robot's behavior to successfully fulfill the task. Each correction offers information on what the robot should and should not do, where the corrected behavior is more aligned with task objectives than the original behavior. Most prior work on learning from corrections involves interpreting a correction as a new demonstration (consisting of the modified robot behavior), or a preference (for the modified trajectory compared to the robot's original behavior). However, this overlooks one essential element of the correction feedback, which is the human's decision to intervene in the robot's behavior in the first place. This decision can be influenced by multiple factors including the robot's task progress, alignment with human expectations, dynamics, motion legibility, and optimality. In this work, we investigate whether the timing of this decision can offer a useful signal for inferring these task-relevant influences. In particular, we investigate three potential applications for this learning signal: (1) identifying features of a robot's motion that may prompt people to correct it, (2) quickly inferring the final goal of a human's correction based on the timing and initial direction of their correction motion, and (3) learning more precise constraints for task objectives. Our results indicate that correction timing results in improved learning for the first two of these applications. Overall, our work provides new insights on the value of correction timing as a signal for robot learning.