Generating Robot Constitutions & Benchmarks for Semantic Safety

Pierre Sermanet, Anirudha Majumdar, Alex Irpan, Dmitry Kalashnikov, Vikas Sindhwani

Keywords: constitutional ai, constitution, safety, benchmark, semantic safety

TL;DR: Robot constitutions for improving robot behavior + benchmark to evaluate robot behavior

Abstract: Large vision and language models are being increasingly deployed on real robots, leading to an immediate need for ensuring robot safety under AI-control. In this paper, we develop the ASIMOV Benchmark — a collection of large-scale semantic safety datasets grounded in real-world visual scenes and human injury reports from hospitals (500k situations, 3M instructions). We propose a scalable recipe for data generation leveraging text and image generation techniques to synthesize safety-relevant scenarios. As a second contribution, we develop a framework to automatically generate robot constitutions from real-world data to steer a robot’s behavior using Constitutional AI mechanisms. We report a top alignment rate of 84.3% on the ASIMOV Benchmark using generated constitutions, outperforming no-constitution baselines and human-written constitutions. We argue that human interpretability and modifiability of constitutions inferred from data make them an ideal medium for behavior governance of AI-controlled robots.

Submission Number: 662