STAMP: Scalable Task And Model-agnostic Collaborative Perception
This addresses the challenge of integrating diverse agents in autonomous driving systems, offering a scalable and secure solution for improved perception, though it appears incremental as it builds on existing collaborative perception methods.
The paper tackles the problem of multi-agent collaborative perception in autonomous driving by proposing STAMP, a scalable task- and model-agnostic pipeline that uses lightweight adapter-reverter pairs to enable efficient feature sharing among heterogeneous agents, achieving comparable or superior accuracy to state-of-the-art models with significantly reduced computational costs.
Perception is crucial for autonomous driving, but single-agent perception is often constrained by sensors' physical limitations, leading to degraded performance under severe occlusion, adverse weather conditions, and when detecting distant objects. Multi-agent collaborative perception offers a solution, yet challenges arise when integrating heterogeneous agents with varying model architectures. To address these challenges, we propose STAMP, a scalable task- and model-agnostic, collaborative perception pipeline for heterogeneous agents. STAMP utilizes lightweight adapter-reverter pairs to transform Bird's Eye View (BEV) features between agent-specific and shared protocol domains, enabling efficient feature sharing and fusion. This approach minimizes computational overhead, enhances scalability, and preserves model security. Experiments on simulated and real-world datasets demonstrate STAMP's comparable or superior accuracy to state-of-the-art models with significantly reduced computational costs. As a first-of-its-kind task- and model-agnostic framework, STAMP aims to advance research in scalable and secure mobility systems towards Level 5 autonomy. Our project page is at https://xiangbogaobarry.github.io/STAMP and the code is available at https://github.com/taco-group/STAMP.