RCA: Ride Comfort-Aware Visual Navigation via Self-Supervised Learning
This addresses ride comfort for wheelchair users in shared autonomy navigation, representing an incremental improvement by focusing on perceived motion rather than geometric or semantic models.
The paper tackled the problem of enabling vehicles to navigate with human-preferred ride comfort by explicitly modeling traversability based on perceived motion intensity, using a self-supervised learning framework that predicts costmaps from images. The result showed improved ride comfort in robot experiments and human evaluations.
Under shared autonomy, wheelchair users expect vehicles to provide safe and comfortable rides while following users high-level navigation plans. To find such a path, vehicles negotiate with different terrains and assess their traversal difficulty. Most prior works model surroundings either through geometric representations or semantic classifications, which do not reflect perceived motion intensity and ride comfort in downstream navigation tasks. We propose to model ride comfort explicitly in traversability analysis using proprioceptive sensing. We develop a self-supervised learning framework to predict traversability costmap from first-person-view images by leveraging vehicle states as training signals. Our approach estimates how the vehicle would feel if traversing over based on terrain appearances. We then show our navigation system provides human-preferred ride comfort through robot experiments together with a human evaluation study.