SPARK: A Modular Benchmark for Humanoid Robot Safety

2025-02-05

AI Summary

This paper addresses safety risks arising from the strong physical interaction capabilities of humanoid robots in autonomous and teleoperated scenarios. We propose SPARK, the first modular safety benchmark specifically designed for humanoid robots. Methodologically, we introduce a novel composable and configurable safety control framework that enables unified evaluation across diverse environments, tasks, and robot models, with seamless deployment from simulation (Unity/Isaac Sim) to real hardware (Unitree G1), integrated with ROS 2, Apple Vision Pro, and motion-capture sensor fusion. Our contributions are: (1) a modular architecture featuring real-time safety constraint solving; (2) cross-platform hardware abstraction and multimodal sensor fusion; (3) systematic evaluation of multiple safety strategies in simulation and empirical validation of real-time safety control efficacy on physical hardware; and (4) open-sourcing of all code to advance community-driven safety standardization.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

This paper introduces the Safe Protective and Assistive Robot Kit (SPARK), a comprehensive benchmark designed to ensure safety in humanoid autonomy and teleoperation. Humanoid robots pose significant safety risks due to their physical capabilities of interacting with complex environments. The physical structures of humanoid robots further add complexity to the design of general safety solutions. To facilitate the safe deployment of complex robot systems, SPARK can be used as a toolbox that comes with state-of-the-art safe control algorithms in a modular and composable robot control framework. Users can easily configure safety criteria and sensitivity levels to optimize the balance between safety and performance. To accelerate humanoid safety research and development, SPARK provides a simulation benchmark that compares safety approaches in a variety of environments, tasks, and robot models. Furthermore, SPARK allows quick deployment of synthesized safe controllers on real robots. For hardware deployment, SPARK supports Apple Vision Pro (AVP) or a Motion Capture System as external sensors, while also offering interfaces for seamless integration with alternative hardware setups. This paper demonstrates SPARK's capability with both simulation experiments and case studies with a Unitree G1 humanoid robot. Leveraging these advantages of SPARK, users and researchers can significantly improve the safety of their humanoid systems as well as accelerate relevant research. The open-source code is available at https://github.com/intelligent-control-lab/spark.

Problem

• Ensures safety in humanoid robot autonomy
• Facilitates safe deployment of complex robot systems
• Accelerates humanoid safety research and development

Innovation

• Modular safe control algorithms
• Simulation benchmark for safety
• Quick deployment on real robots