Search papers, labs, and topics across Lattice.
6
4
7
2
Multi-robot coordination doesn't need to turn each robot into a fragmented multi-agent system; treating them as federated single agents actually improves governance and recovery.
Current embodied AI benchmarks overlook critical governance aspects like controllability and safety during upgrades, a gap EmbodiedGovBench directly addresses.
Forget retraining your robot from scratch: this capability-centric approach lets embodied agents learn new tricks without losing their core identity or safety guarantees.
Guaranteeing safe and reliable behavior in embodied agents requires external runtime governance, not just smarter agents.
Naive upgrades of embodied agent capabilities lead to unsafe activations in 60% of cases, but a governed upgrade framework can maintain task success while ensuring zero unsafe activations.
Robots can achieve 100% task success and maintain safety across diverse tasks by modeling them as single agents with hot-swappable capability modules governed by a policy-separated runtime.
