Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
Robots can learn to sacrifice immediate gains for superior team coordination, outperforming centralized and reactive planners even with over a thousand agents.
Swapping traditional numerical trajectory optimization for parallel diffusion denoising resolves complex multi-robot deadlocks faster and more reliably than MPPI, scaling seamlessly to 100 agents and zero-shot real-world drone swarms.
