Interpreting Context-Aware Human Preferences for Multi-Objective Robot Navigation

TL;DR

This paper introduces a pipeline that enables robots to interpret and adapt to human preferences in real-time navigation by combining vision-language models, large language models, and multi-objective reinforcement learning.

Contribution

It presents a novel integration of semantic reasoning and low-level control allowing robots to understand natural language preferences in context and adapt their navigation accordingly.

Findings

System reliably captures user intent and preferences.

Enables real-time, context-dependent navigation adaptation.

Improves robot transparency and usability in human environments.

Abstract

Robots operating in human-shared environments must not only achieve task-level navigation objectives such as safety and efficiency, but also adapt their behavior to human preferences. However, as human preferences are typically expressed in natural language and depend on environmental context, it is difficult to directly integrate them into low-level robot control policies. In this work, we present a pipeline that enables robots to understand and apply context-dependent navigation preferences by combining foundational models with a Multi-Objective Reinforcement Learning (MORL) navigation policy. Thus, our approach integrates high-level semantic reasoning with low-level motion control. A Vision-Language Model (VLM) extracts structured environmental context from onboard visual observations, while Large Language Models (LLM) convert natural language user feedback into interpretable, context-dependent behavioral rules stored in a persistent but updatable rule memory. A preference translation module then maps contextual information and stored rules into numerical preference vectors that parameterize a pretrained MORL policy for real-time navigation adaptation. We evaluate the proposed framework through quantitative component-level evaluations, a user study, and real-world robot deployments in various indoor environments. Our results demonstrate that the system reliably captures user intent, generates consistent preference vectors, and enables controllable behavior adaptation across diverse contexts. Overall, the proposed pipeline improves the adaptability, transparency, and usability of robots operating in shared human environments, while maintaining safe and responsive real-time control.