← Back to Benchmarks
simmediumnavigationmetric · varies
SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning
Description
Sequential-Horizon Vision-and-Language Navigation (SH-VLN) presents a challenging scenario where agents should sequentially execute multi-task navigation guided by complex, long-horizon language instructions. Current vision-and-language navigation models exhibit significant performance degradation with such multi-task instructions, as information overload impairs the agent's ability to attend to observationally relevant details. To address this problem, we propose SeqWalker, a navigation model b