LT-Exosense: A Vision-centric Multi-session Mapping System for Lifelong Safe Navigation of Exoskeletons

TL;DR

LT-Exosense is a vision-based multi-session mapping system that enables lifelong safe navigation for exoskeletons by incrementally building and updating a global map, supporting adaptive path planning in changing environments.

Contribution

It introduces a novel multi-session mapping system that fuses spatial knowledge over time for exoskeleton navigation, handling environmental changes effectively.

Findings

Achieves less than 5 cm average point-to-point error.

Supports adaptive path planning in dynamic indoor environments.

Demonstrates scalability through real-world experiments.

Abstract

Self-balancing exoskeletons offer a promising mobility solution for individuals with lower-limb disabilities. For reliable long-term operation, these exoskeletons require a perception system that is effective in changing environments. In this work, we introduce LT-Exosense, a vision-centric, multi-session mapping system designed to support long-term (semi)-autonomous navigation for exoskeleton users. LT-Exosense extends single-session mapping capabilities by incrementally fusing spatial knowledge across multiple sessions, detecting environmental changes, and updating a persistent global map. This representation enables intelligent path planning, which can adapt to newly observed obstacles and can recover previous routes when obstructions are removed. We validate LT-Exosense through several real-world experiments, demonstrating a scalable multi-session map that achieves an average point-to-point error below 5 cm when compared to ground-truth laser scans. We also illustrate the potential application of adaptive path planning in dynamically changing indoor environments.