AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

SafeLab: An Interactive High-Fidelity Benchmark for Embodied Safety in Scientific Robotics

Fengshuo Bai, Yufeng Li, Ruihai Wu, Peishuo Wang, Yuhan Wang, Bernie Hao Zhu, Yuanfei Wang, Tawei Chou, Jing Gao, Runchuan Zhu, Ying Wen, Yaodong Yang and 1 more

ICML 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add bounded residual RL with trajectory-level safety penalties on a frozen IL policyDP · SafeLab nominalSSR domain average: 32.5 -> 75.5 (+43.0)Improved
add bounded residual RL on a frozen IL policypi0.5 · SafeLab nominalSSR domain average: 52.9 -> 86.0 (+33.1)Improved
add residual RL under visual/physical/spatial perturbationsDP · SafeLab perturbedSSR average: 25.6 -> 70.6Improved
add residual RL under visual/physical/spatial perturbationspi0.5 · SafeLab perturbedSSR average: 42.1 -> 79.5Improved
raise residual scale alpha from 0.10 to 0.30 (ablation)DP + residual RL · SafeLab LiquidSSR: 73.2 -> 64.1Hurt
raise residual scale alpha from 0.10 to 0.20 (ablation)DP + residual RL · SafeLab SpatialSSR: 78.9 -> 81.3Improved
lower residual scale alpha from 0.10 to 0.05 (ablation)DP + residual RL · SafeLab LiquidSSR: 73.2 -> 68.4Hurt
use constrained RL variants instead of penalty reward (ablation)residual RL · SafeLab LiquidSSR / training cost: 1.8-2.1x training costNo clear effect
larger injected base-policy perturbation (small to large) (ablation)DP + residual RL, alpha 0.1 · Recovery under injected perturbationrecovery rate: 88% -> 17%Hurt
evaluate with safety (SSR) instead of task success (SR)VLA/IL policies · SafeLab all domainssuccess rate gap: SSR trails SR by more than 30 pointsHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy