SANGO: Socially Aware Navigation through Grouped Obstacles
This addresses the problem of enabling robots to navigate safely and appropriately in human-populated environments, representing an incremental advance in socially aware navigation methods.
This paper tackles the problem of socially appropriate robot navigation in crowded environments by introducing SANGO, a method that dynamically groups obstacles and adheres to social norms using deep reinforcement learning. The result shows significant improvements, including up to 83.5% reduction in discomfort, 29.4% reduction in collision rates, and higher successful navigation in dynamic scenarios.
This paper introduces SANGO (Socially Aware Navigation through Grouped Obstacles), a novel method that ensures socially appropriate behavior by dynamically grouping obstacles and adhering to social norms. Using deep reinforcement learning, SANGO trains agents to navigate complex environments leveraging the DBSCAN algorithm for obstacle clustering and Proximal Policy Optimization (PPO) for path planning. The proposed approach improves safety and social compliance by maintaining appropriate distances and reducing collision rates. Extensive experiments conducted in custom simulation environments demonstrate SANGO's superior performance in significantly reducing discomfort (by up to 83.5%), reducing collision rates (by up to 29.4%) and achieving higher successful navigation in dynamic and crowded scenarios. These findings highlight the potential of SANGO for real-world applications, paving the way for advanced socially adept robotic navigation systems.