Xu and Liu formalize multi-agent VLN as a constrained coordination problem where missions comprise subtasks with dependency constraints (presence locks and holding chains) and resource constraints (agent availability).
First benchmark and method for team-based vision-and-language navigation under constraints
The authors formalize multi-agent VLN as a constrained coordination problem, introduce a benchmark with 11,724 episodes, and propose TRISS as a coordination-ready navigation system.
Independent
Yunzhe Xu · Zhe Liu
Research Digest··2 min read
Xu and Liu present the first systematic formalization of multi-agent Vision-and-Language Navigation (VLN) as a coordination problem with subtask dependencies, resource constraints, and collision avoidance.
Why this paper
Independent
In one line
The first systematic formalization of multi-agent VLN as constrained coordination, with benchmark MAVLN and method TRISS.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§