{"ID":2894607,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.09836","arxiv_id":"2507.09836","title":"Multi-residual Mixture of Experts Learning for Cooperative Control in Multi-vehicle Systems","abstract":"Autonomous vehicles (AVs) are becoming increasingly popular, with their applications now extending beyond just a mode of transportation to serving as mobile actuators of a traffic flow to control flow dynamics. This contrasts with traditional fixed-location actuators, such as traffic signals, and is referred to as Lagrangian traffic control. However, designing effective Lagrangian traffic control policies for AVs that generalize across traffic scenarios introduces a major challenge. Real-world traffic environments are highly diverse, and developing policies that perform robustly across such diverse traffic scenarios is challenging. It is further compounded by the joint complexity of the multi-agent nature of traffic systems, mixed motives among participants, and conflicting optimization objectives subject to strict physical and external constraints. To address these challenges, we introduce Multi-Residual Mixture of Expert Learning (MRMEL), a novel framework for Lagrangian traffic control that augments a given suboptimal nominal policy with a learned residual while explicitly accounting for the structure of the traffic scenario space. In particular, taking inspiration from residual reinforcement learning, MRMEL augments a suboptimal nominal AV control policy by learning a residual correction, but at the same time dynamically selects the most suitable nominal policy from a pool of nominal policies conditioned on the traffic scenarios and modeled as a mixture of experts. We validate MRMEL using a case study in cooperative eco-driving at signalized intersections in Atlanta, Dallas Fort Worth, and Salt Lake City, with real-world data-driven traffic scenarios. The results show that MRMEL consistently yields superior performance-achieving an additional 4%-9% reduction in aggregate vehicle emissions relative to the strongest baseline in each setting.","short_abstract":"Autonomous vehicles (AVs) are becoming increasingly popular, with their applications now extending beyond just a mode of transportation to serving as mobile actuators of a traffic flow to control flow dynamics. This contrasts with traditional fixed-location actuators, such as traffic signals, and is referred to as Lagr...","url_abs":"https://arxiv.org/abs/2507.09836","url_pdf":"https://arxiv.org/pdf/2507.09836v1","authors":"[\"Vindula Jayawardana\",\"Sirui Li\",\"Yashar Farid\",\"Cathy Wu\"]","published":"2025-07-14T00:17:12Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.LG\",\"cs.MA\",\"eess.SY\"]","methods":"[\"Mixture of Experts\",\"Reinforcement Learning\"]","has_code":false}