C-MASS: Combinatorial Mobility-Aware Sensor Scheduling for Collaborative Perception with Second-Order Topology Approximation

TL;DR

This paper introduces C-MASS, a sensor scheduling framework for collaborative perception in vehicular networks that maintains perception topology with minimal communication, improving detection recall and near-optimality.

Contribution

It proposes a novel combinatorial, mobility-aware sensor scheduling method that approximates perception topology with second-order data, balancing exploration and exploitation under mobility constraints.

Findings

Achieves 5.8% and 4.2% weighted recall improvements in edge-assisted and distributed setups.

Reduces gap to offline optimal solutions by up to 75% and 71%.

Demonstrates near-optimal performance through extensive numerical experiments.

Abstract

Collaborative Perception (CP) has been a promising solution to address occlusions in the traffic environment by sharing sensor data among collaborative vehicles (CoV) via vehicle-to-everything (V2X) network. With limited wireless bandwidth, CP necessitates task-oriented and receiver-aware sensor scheduling to prioritize important and complementary sensor data. However, due to vehicular mobility, it is challenging and costly to obtain the up-to-date perception topology, i.e., whether a combination of CoVs can jointly detect an object. In this paper, we propose a combinatorial mobility-aware sensor scheduling (C-MASS) framework for CP with minimal communication overhead. Specifically, detections are replayed with sensor data from individual CoVs and pairs of CoVs to maintain an empirical perception topology up to the second order, which approximately represents the complete perception topology. A hybrid greedy algorithm is then proposed to solve a variant of the budgeted maximum coverage problem with a worst-case performance guarantee. The C-MASS scheduling algorithm adapts the greedy algorithm by incorporating the topological uncertainty and the unexplored time of CoVs to balance exploration and exploitation, addressing the mobility challenge. Extensive numerical experiments demonstrate the near-optimality of the proposed C-MASS framework in both edge-assisted and distributed CP configurations. The weighted recall improvements over object-level CP are 5.8% and 4.2%, respectively. Compared to distance-based and area-based greedy heuristics, the gaps to the offline optimal solutions are reduced by up to 75% and 71%, respectively.