Low-Burden LLM-Based Preference Learning: Personalizing Assistive Robots from Natural Language Feedback for Users with Paralysis
Authors: Keshav Shankar, Dan Ding, Wei Gao
Organizations: Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA. · Rehabilitation Science and Technology, University of Pittsburgh, Pittsburgh, PA.
Physically Assistive Robots require personalized behaviors to ensure user safety and comfort. However, traditional preference learning methods, like exhaustive pairwise comparisons, cause substantial physical and cognitive fatigue for users with severe motor impairments. To solve this, we propose a low-burden, offline framework that translates unstructured natural language feedback directly into deterministic robotic control policies. To safely bridge the gap between ambiguous human speech and robotic code, our pipeline uses Large Language Models (LLMs) grounded in the Occupational Therapy Practice Framework. This clinical reasoning decodes subjective user reactions into explicit physical and psychological needs, which are then mapped into transparent decision trees. Before deployment, an automated "LLM-as-a-Judge" verifies the code's structural safety. We validated this system in a simulated meal preparation study with 10 adults with paralysis. Results show our natural language approach significantly reduces user workload compared to traditional baselines. Additionally, occupational therapists confirmed the generated policies are safe and accurately reflect user preferences.
Figures & tables
Fig. 1: High-burden pairwise comparisons (left) versus our proposed low-burden natural language (right) preferences.
Fig. 2: Proposed pipeline for translating unstructured natural language feedback into verifiable robotic policies.
Fig. 3: Overview of the LLM prompt structures, including roles, inputs, instructions, and outputs for the pipeline.
Fig. 4: Simulated kitchen environment with target objects, user, and robot.
FIM Category
Average
Max
Std. Dev.
Motor Domain
Self-care
22.4
42
11.7
Sphincter Control
8.5
14
4.7
Transfers
11.0
21
7.4
Locomotion
6.2
14
3.1
Cognitive Domain
TABLE I: Aggregate FIM Scores
Fig. 5: Distribution of NASA-TLX subscale scores across the three elicitation methods: questionnaire (M1), pairwise comparison (M2), and natural language feedback (M3). Solid bars represent mean scores, error bars denote the standard error of the mean, and black dots indicate individual participant scores. Lower scores indicate lower perceived user burden. Scoring for the Performance subscale is inverted.
Fig. 6: Independent clinician validation of the system’s reasoning traces on a 5-point Likert scale. Evaluators assessed adherence to the OTPF evaluation sequence (Q1), correct application of domain terminology (Q2), and logical grounding in raw user feedback (Q3).
Fig. 7: Performance of the LLM Judge on 360 structurally perturbed policies. Actual assigned scores are plotted against target scores (injected violations) across three structural evaluation criteria: Atomic Conditions (C1), Distinct Branches (C2), and Valid Closed Logic (C3).
Fig. 8: User evaluation of end-to-end policy alignment on a 5-point Likert scale. Users assessed the appropriateness of derived movement speed (Q1), notification frequency (Q2), and standoff distance (Q3), as well as their willingness to use the robot (Q4) and clear understanding of its behavior (Q5).
Fig. 9: Independent clinical safety check of the mapped robot policies on a 5-point Likert scale. Clinicians evaluated physical/practical risk avoidance (Q1) and accurate alignment with the user’s explicit preferences (Q2).