BestHub
Sign in
Data Party THU
Data Party THU
Apr 5, 2026 · Artificial Intelligence

How Sequential World Models Enable Scalable Multi‑Robot Cooperation

SeqWM introduces a sequential causal decomposition of multi‑robot dynamics, allowing each robot to model its marginal contribution conditioned on preceding agents, which simplifies learning, improves sample efficiency, and yields natural collaborative behaviors both in simulation (Bi‑DexHands, Multi‑Quadruped) and real‑world tests on Unitree Go2‑W, outperforming prior methods.

multi-robotreal-robotreinforcement-learning
0 likes · 7 min read
How Sequential World Models Enable Scalable Multi‑Robot Cooperation
Huawei Cloud Developer Alliance
Huawei Cloud Developer Alliance
May 6, 2023 · Artificial Intelligence

How We Won a Multi‑Robot Competition: Greedy Scheduling, A* Pathfinding, and Dynamic Window Control

This article details the end‑to‑end algorithmic strategy our team used to rank third in a multi‑robot competition, covering task analysis, distance‑based scheduling, custom collision detection, A* and DWA path planning, Euclidean distance transforms, radar‑based enemy tracking, and the final round’s dual‑team tactics, complete with code snippets and performance insights.

BFSatcollision detection
0 likes · 39 min read
How We Won a Multi‑Robot Competition: Greedy Scheduling, A* Pathfinding, and Dynamic Window Control