FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers' Preference Elicitation
Not on the map. Why?
Abstract (arXiv)
Preference-based learning aims to align robot task objectives with human values. One of the most common methods to infer human preferences is by pairwise comparisons of robot task trajectories. Traditional comparison-based preference labeling systems seldom support labelers to digest and identify critical differences between complex trajectories recorded in videos. Our formative study (N = 12) suggests that individuals may overlook non-salient task features and establish biased preference criteria during their preference elicitation process because of partial observations. In addition, they may experience mental fatigue when given many pairs to compare, causing their label quality to deteriorate. To mitigate these issues, we propose FARPLS, a Feature-Augmented Robot trajectory Preference Labeling System. FARPLS highlights potential outliers in a wide variety of task features that matter to humans and extracts the corresponding video keyframes for easy review and comparison. It also dynamically adjusts the labeling order according to users' familiarities, difficulties of the trajectory pair, and level of disagreements. At the same time, the system monitors labelers' consistency and provides feedback on labeling progress to keep labelers engaged. A between-subjects study (N = 42, 105 pairs of robot pick-and-place trajectories per person) shows that FARPLS can help users establish preference criteria more easily and notice more relevant details in the presented trajectories than the conventional interface. FARPLS also improves labeling consistency and engagement, mitigating challenges in preference elicitation without raising cognitive loads significantly
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 93 references that are in the map. First posted on arXiv 10 Mar 2024.
Builds on
21 of 93 references.
References · 21
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2017Deep reinforcement learning from human preferencescited by 3,846
- 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
- 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
- 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
- 2023Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisonscited by 244
- 2019The VIA Annotation Software for Images, Audio and Videocited by 166
- 2023Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimismcited by 69
- 2019Asking Easy Questions: A User-Friendly Approach to Active Reward Learningcited by 67
- 2023Benchmarks and Algorithms for Offline Preference-Based Reward Learningcited by 55
- 2020Feature Expansive Reward Learning: Rethinking Human Inputcited by 25
- 2021Learning Reward Functions from Scale Feedbackcited by 24
9 more
- 2023Perspectives on the Social Impacts of Reinforcement Learning with Human Feedbackcited by 15
- 2014Eliciting Single-Peaked Preferences Using Comparison Queriescited by 12
- 2020Human-guided Robot Behavior Learning: A GAN-assisted Preference-based Reinforcement Learning Approachcited by 10
- 2022OneLabeler: A Flexible System for Building Data Labeling Toolscited by 9
- 2019Semi-Automatic Labeling for Deep Learning in Roboticscited by 8
- 2021Annotation Curricula to Implicitly Train Non-Expert Annotatorscited by 8
- 2021Here's What I've Learned: Asking Questions that Reveal Reward Learningcited by 8
- 2022MyMove: Facilitating Older Adults to Collect In-Situ Activity Labels on a Smartwatch with Speechcited by 4
- 2022A User Interface for Sense-making of the Reasoning Process while Interacting with Robotscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.