Real test system compares social navigation methods for service robots
RESONATE: a Real Social Navigation Testbed for Autonomous Service Robots
Robotics
Summary
Moving around people safely and politely is hard for robots. The authors created RESONATE, a common setup to test how well different robot navigation methods handle social situations in real life. They ran many experiments with various planning methods to see which balanced safety, efficiency, and how comfortable people felt around the robots. Their results showed some methods work better in different scenarios, giving clear guidance on what approaches work well for robots navigating around people. This test setup helps others build and evaluate robots that move better in human environments.
What this means in practice
- •For robotics engineers: Use RESONATE to benchmark and improve robot navigation algorithms in real social environments with standardized metrics and scenarios.
- •For service robot developers: Develop robots that navigate safely and comfortably around people using validated controller configurations tested on the RESONATE real-world platform.
Authors
Stefano Trepella, Andrea Ostuni, Mauro Martini, Irene Borgini, Marcello Chiaberge
Abstract
Social navigation is essential for autonomous service robots operating in human environments, but progress remains constrained by the lack of extensive real-world benchmarks. This paper presents the Real Social Navigation Testbed (RESONATE), a reproducible benchmark for human-aware navigation based on a unified robotic platform, a shared ROS 2 software stack, precise trajectory ground truth, and structured social interaction scenarios. We evaluate eight controller configurations, combining classical and predictive local planners with different social modeling strategies, over eight representative scenarios with five repetitions each, yielding 320 physical experiments. The benchmark combines quantitative navigation and social metrics with participant-based qualitative assessments to jointly measure efficiency, safety, comfort, and perceived social behavior. Results reveal scenario-dependent trade-offs among the tested methods. The algorithms that stands out for their performance are the DWA with Gaussian social costmaps for its reliability, and the SFM-MPPI to provide the best balance between robustness, navigation efficiency, and social acceptance. Overall, RESONATE supports the robotics community with a real-world benchmark, reusable baselines, data, and testbed, and a consistent evaluation protocol for advancing socially aware navigation research.