NEXUS: Safe planning for embodied agents with learned safety constraints
In brief
- NEXUS combines PDDL models and LTL specifications for safe embodied agent planning.
- It repairs execution failures and accumulates reusable safety constraints.
- Achieves the best trade-off between safe task completion and unsafe task refusal on SafeAgentBench.
NEXUS is a neuro-symbolic framework that integrates a PDDL action model and an LTL safety specification for embodied agents. It corrects execution failures and accumulates reusable safety constraints, improving the balance between safe task completion and refusal of unsafe tasks.
What it changes for you
- Industry & ManufacturingEnables industrial robots to plan tasks while adhering to dynamic and reusable safety constraints.
This summary gives you the essentials. The full article, its figures and quotes are on cs.AI updates on arXiv.org.
Read the original articleAI-generated summary of the source, checked by rules. Report an error