VLM-Based Advanced Rider Assistance System for Motorcycle Safety

2026-05-27

AI Summary

This work addresses the disproportionately high accident rates of motorcycles—attributable to their lack of structural protection and heightened sensitivity to road hazards—and the lagging development of rider-assist systems. To bridge this gap, the study introduces vision-language models (VLMs) into motorcycle risk perception for the first time, generating pixel-wise, interpretable dense risk maps by fusing semantic segmentation with physical attributes. Furthermore, it proposes a sampling-based motion planner tailored to motorcycle dynamics, which outputs safe throttle and steering commands. Experiments in the CARLA simulation platform demonstrate that the proposed approach significantly improves task success rates and reduces risk exposure compared to baseline methods, while simultaneously producing explainable risk maps and safe trajectories.

Abstract

Motorcycles face disproportionately high crash risks compared to cars due to limited protection and heightened sensitivity to surface hazards, yet Advanced Rider Assistance Systems (ARAS) remain underdeveloped relative to Advanced Driver Assistance Systems (ADAS). We propose a novel ARAS that enhances motorcycle safety through semantic perception and risk-aware planning. Our approach leverages Vision-Language Models (VLMs) for contextual hazard reasoning and integrates them with segmentation-based detection to construct dense risk maps. These maps encode both semantic characteristics (e.g., pothole severity, puddle slipperiness) and physical attributes (e.g., size, depth), which produce per-pixel hazard costs that capture motorcycle-specific risks. These maps are used by a sampling-based planner tailored to motorcycle dynamics to recommend throttle and steering actions that minimize hazard exposure while advancing toward the destination. We evaluate our system in different scenarios in the CARLA simulator. Compared to the baseline method, our method achieves higher success rates and lower hazard exposure, while qualitative results demonstrate interpretable risk maps and safe trajectory recommendations.

Problem

• motorcycle safety
• Advanced Rider Assistance System
• hazard perception
• risk-aware planning
• Vision-Language Models

Innovation

• Vision-Language Models
• Motorcycle Safety
• Risk-Aware Planning
• Semantic Perception
• Advanced Rider Assistance System