Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SAATT Nav: a Socially Aware Autonomous Transparent Transportation Navigation Framework for Wheelchairs

Yutong Zhang, Shaiv Y. Mehra, Bradley S. Duerstock, Juan P. Wachs

Abstract

While powered wheelchairs reduce physical fatigue as opposed to manual wheelchairs for individuals with mobility impairment, they demand high cognitive workload due to information processing, decision making and motor coordination. Current autonomous systems lack social awareness in navigation and transparency in decision-making, leading to decreased perceived safety and trust from the user and others in context. This work proposes Socially Aware Autonomous Transparent Transportation (SAATT) Navigation framework for wheelchairs as a potential solution. By implementing a Large Language Model (LLM) informed of user intent and capable of predicting other peoples' intent as a decision-maker for its local controller, it is able to detect and navigate social situations, such as passing pedestrians or a pair conversing. Furthermore, the LLM textually communicates its reasoning at each waypoint for transparency. In this experiment, it is compared against a standard global planner, a representative competing social navigation model, and an Ablation study in three simulated environments varied by social levels in eight metrics categorized under Safety, Social Compliance, Efficiency, and Comfort. Overall, SAATT Nav outperforms in most social situations and equivalently or only slightly worse in the remaining metrics, demonstrating the potential of a socially aware and transparent autonomous navigation system to assist wheelchair users.

SAATT Nav: a Socially Aware Autonomous Transparent Transportation Navigation Framework for Wheelchairs

Abstract

While powered wheelchairs reduce physical fatigue as opposed to manual wheelchairs for individuals with mobility impairment, they demand high cognitive workload due to information processing, decision making and motor coordination. Current autonomous systems lack social awareness in navigation and transparency in decision-making, leading to decreased perceived safety and trust from the user and others in context. This work proposes Socially Aware Autonomous Transparent Transportation (SAATT) Navigation framework for wheelchairs as a potential solution. By implementing a Large Language Model (LLM) informed of user intent and capable of predicting other peoples' intent as a decision-maker for its local controller, it is able to detect and navigate social situations, such as passing pedestrians or a pair conversing. Furthermore, the LLM textually communicates its reasoning at each waypoint for transparency. In this experiment, it is compared against a standard global planner, a representative competing social navigation model, and an Ablation study in three simulated environments varied by social levels in eight metrics categorized under Safety, Social Compliance, Efficiency, and Comfort. Overall, SAATT Nav outperforms in most social situations and equivalently or only slightly worse in the remaining metrics, demonstrating the potential of a socially aware and transparent autonomous navigation system to assist wheelchair users.
Paper Structure (26 sections, 10 equations, 4 figures, 2 tables, 1 algorithm)

This paper contains 26 sections, 10 equations, 4 figures, 2 tables, 1 algorithm.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. Current Autonomous Wheelchair Navigation
  4. Social and Human Behavior Models
  5. Problem Definition
  6. Method
  7. System Overview
  8. LLM-Based Hypothesis Generator
  9. Rollout-Based Hypothesis Scorer
  10. Rule-Based Motion Planner
  11. Baseline Methods
  12. EXPERIMENTAL SETUP
  13. Simulation Environment
  14. Scenarios
  15. Randomization and Paired Design
  16. ...and 11 more sections

Figures (4)

  • Figure 1: Overview of the SAATT Navigation Framework.
  • Figure 2: Radar plots for performance metrics across scenarios, normalized via Min-Max Scaling. Complements were found for all but Success and Minimum Pedestrian Distance to ensure the outer ring correlates to better performance.
  • Figure 3: Trajectory comparison across all four methods in Scenario A (left), B (center), and C (right) for a representative seed.
  • Figure 4: Qualitative results of the proposed framework in Scenario C, showing wheelchair trajectory, LLM refresh events, and predicted pedestrian intents to demonstrating transparency.