Search papers, labs, and topics across Lattice.
This paper introduces Systematic Multi-Agent Vision-and-Language Navigation (MAVLN), formalizing multi-agent VLN as a constrained coordination problem with dependency and resource constraints. A benchmark of 11,724 episodes across 145 scenes is created, featuring teams of up to four agents and new constraint-aware metrics. The proposed TRISS system, integrating an LLM scheduler, shared memory, and conflict-aware execution, sets a baseline and reveals significant challenges in multi-agent coordination under these complex task constraints.
Real-world multi-robot coordination in vision-and-language tasks is now formally defined and benchmarked, revealing that current systems struggle with even basic dependency and resource constraints.
Vision-and-Language Navigation (VLN) has largely focused on a single agent following a single instruction, yet many real-world applications require teams of robots to tackle tasks beyond the capabilities of any individual agent. We present Systematic Multi-Agent Vision-and-Language Navigation, providing, to our knowledge, the first systematic formalization of multi-agent VLN as a constrained coordination problem: each mission consists of subtasks carrying dependency and resource constraints (presence locks and holding chains). A verified four-stage crafting pipeline instantiates the task as MAVLN, comprising 11,724 episodes across 145 scenes with teams of up to four agents under three instruction regimes, accompanied by tailored constraint-aware metrics. We further present TRISS, a coordination-ready navigation system coupling an LLM-based subtask scheduler, a shared topological memory that turns each agent's exploration into team knowledge, and a conflict-aware execution mechanism that realizes simultaneous intentions as collision-free routes. Extensive experiments establish TRISS as a comprehensive baseline and reveal substantial room for improvement across scheduling, planning, and execution, highlighting the challenges of coordinating under MAVLN task constraints. Project page: https://xyz9911.github.io/mavln.
