Towards Autonomous Micromobility through Scalable Urban Simulation

2025-05-01

AI Summary

To address the low safety and inefficiency of manual operation of micro-mobility devices (e.g., delivery robots, e-scooters) in complex urban environments, this paper introduces URBAN-SIM—a high-fidelity, scalable, physics-engine-driven urban simulation platform enabling large-scale embodied reinforcement learning for multi-modal micro-robots (e.g., wheeled, legged). Methodologically, it innovatively integrates hierarchical city generation, interactive dynamics modeling, and asynchronous scenario sampling. It also proposes URBAN-BENCH—the first systematic, three-dimensional autonomy benchmark encompassing traversal, navigation, and crossing—enabling fair cross-platform evaluation across robot morphologies. Extensive experiments across diverse urban terrains evaluate eight tasks, revealing performance boundaries and adaptive behavioral patterns of distinct robot configurations under dynamic human-robot coexistence. Results demonstrate URBAN-SIM’s capacity to support robust, generalizable policy learning and provide empirical insights into morphology-dependent autonomy limitations in realistic urban settings.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Micromobility, which utilizes lightweight mobile machines moving in urban public spaces, such as delivery robots and mobility scooters, emerges as a promising alternative to vehicular mobility. Current micromobility depends mostly on human manual operation (in-person or remote control), which raises safety and efficiency concerns when navigating busy urban environments full of unpredictable obstacles and pedestrians. Assisting humans with AI agents in maneuvering micromobility devices presents a viable solution for enhancing safety and efficiency. In this work, we present a scalable urban simulation solution to advance autonomous micromobility. First, we build URBAN-SIM - a high-performance robot learning platform for large-scale training of embodied agents in interactive urban scenes. URBAN-SIM contains three critical modules: Hierarchical Urban Generation pipeline, Interactive Dynamics Generation strategy, and Asynchronous Scene Sampling scheme, to improve the diversity, realism, and efficiency of robot learning in simulation. Then, we propose URBAN-BENCH - a suite of essential tasks and benchmarks to gauge various capabilities of the AI agents in achieving autonomous micromobility. URBAN-BENCH includes eight tasks based on three core skills of the agents: Urban Locomotion, Urban Navigation, and Urban Traverse. We evaluate four robots with heterogeneous embodiments, such as the wheeled and legged robots, across these tasks. Experiments on diverse terrains and urban structures reveal each robot's strengths and limitations.

Problem

• Developing AI agents to enhance micromobility safety and efficiency
• Creating scalable urban simulation for autonomous micromobility training
• Evaluating robot performance in diverse urban tasks and environments

Innovation

• High-performance robot learning platform URBAN-SIM
• Hierarchical Urban Generation for diverse simulations
• URBAN-BENCH benchmarks for autonomous micromobility tasks