Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
0
Fragmentation in robot learning systems limits their effectiveness, but a unified framework could enable robots to reason and act more reliably in complex environments.
Human egocentric videos can be transformed into a scalable training resource, boosting mobile robot navigation performance beyond traditional datasets.
Achieve surprisingly strong imitation learning for robotic lab automation using a model under 500M parameters, demonstrating that you don't need massive models for real-world tasks.
LLMs can plan complex robot tasks with 27% less human input by using a mixture-of-agent system to answer questions and behavior trees to structure execution.
