ResponsibleRobotBench: Benchmarking Responsible Robot Manipulation using Multi-modal Large Language Models

TL;DR

ResponsibleRobotBench is a comprehensive benchmark designed to evaluate and advance responsible robotic manipulation, emphasizing safety, risk mitigation, and reasoning across diverse tasks and modalities in simulation and real-world settings.

Contribution

The paper introduces ResponsibleRobotBench, a novel benchmark with diverse tasks, multimodal evaluation framework, and standardized metrics to promote trustworthy and responsible robotic manipulation.

Findings

Benchmark covers 23 multi-stage risk-aware tasks.

Framework supports multimodal perception, reasoning, and physical execution.

Enables analysis of safety and generalization in robotic agents.

Abstract

Recent advances in large multimodal models have enabled new opportunities in embodied AI, particularly in robotic manipulation. These models have shown strong potential in generalization and reasoning, but achieving reliable and responsible robotic behavior in real-world settings remains an open challenge. In high-stakes environments, robotic agents must go beyond basic task execution to perform risk-aware reasoning, moral decision-making, and physically grounded planning. We introduce ResponsibleRobotBench, a systematic benchmark designed to evaluate and accelerate progress in responsible robotic manipulation from simulation to real world. This benchmark consists of 23 multi-stage tasks spanning diverse risk types, including electrical, chemical, and human-related hazards, and varying levels of physical and planning complexity. These tasks require agents to detect and mitigate risks, reason about safety, plan sequences of actions, and engage human assistance when necessary. Our benchmark includes a general-purpose evaluation framework that supports multimodal model-based agents with various action representation modalities. The framework integrates visual perception, context learning, prompt construction, hazard detection, reasoning and planning, and physical execution. It also provides a rich multimodal dataset, supports reproducible experiments, and includes standardized metrics such as success rate, safety rate, and safe success rate. Through extensive experimental setups, ResponsibleRobotBench enables analysis across risk categories, task types, and agent configurations. By emphasizing physical reliability, generalization, and safety in decision-making, this benchmark provides a foundation for advancing the development of trustworthy, real-world responsible dexterous robotic systems. https://sites.google.com/view/responsible-robotbench