Deep Reinforcement-Learning-Guided Model Predictive Control for Preventing Overtakes in Autonomous Racing

• URL: http://arxiv.org/abs/2607.20973v1
• Date: Thu, 23 Jul 2026 06:50:59 GMT
• Title: Deep Reinforcement-Learning-Guided Model Predictive Control for Preventing Overtakes in Autonomous Racing
• Abstract summary: This paper addresses defensive blocking in autonomous racing, where a vehicle must prevent a faster opponent from overtaking while operating near its dynamic limits.<n>We formulate defense as a spatial occupancy regulation problem via a hierarchical reinforcement-learning guided model predictive control framework.<n>The framework achieves a 33.3 ms mean solve time (13.9 ms) supporting real-time high-speed adversarial interaction.
• Score: 1.7396274240172123
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper addresses defensive blocking in autonomous racing, where a vehicle must prevent a faster opponent from overtaking while operating near its dynamic limits. Different from lap-time minimization, we formulate defense as a spatial occupancy regulation problem via a hierarchical reinforcement-learning guided model predictive control framework. A Soft Actor-Critic strategic layer operates in the Frenet domain to generate geometry-aware defensive references, which are embedded into the nonlinear model predictive control formulation as spatial regularization under friction constraints. Evaluated on the Thunderhill West circuit in simulation, the framework increases average overtake time from 8.8 s to 14.6 s while significantly reducing opponent progress. Meanwhile, it allows the vehicle to utilize 83.4% of available tire force. The framework achieves a 33.3 ms mean solve time (13.9 ms std), supporting real-time high-speed adversarial interaction.

Related papers

• Control-Informed Constraint Adaptation in Minimum-Time Trajectory Planning for Autonomous Racing [41.40585589054522]
  Trajectory planners assume perfect tracking and remain blind to execution errors.<n>We introduce a control-informed online trajectory planning framework that learns from its own execution errors.<n>We show that our approach reduces lap time by 1.8,s without increasing computational burden.
  arXiv  Detail & Related papers  (2026-08-14T16:32:12Z)
• Track-Guided Hierarchical Reinforcement Learning for Autonomous Vehicle Drifting with Minimum-Lap-Time Planning [57.68768189557651]
  In Formula 1, drivers optimize racing lines within tire grip limits to minimize lap times.<n>In rally racing, drivers intentionally break traction to drift on loose surfaces.<n>This paper proposes a planning-control framework specifically designed for MLT drifting scenario.
  arXiv  Detail & Related papers  (2026-07-31T08:50:40Z)
• Disturbance-Aware Flight for Aerial Robots in Narrow Space [18.124392684552998]
  This paper presents a disturbance-aware planning and control framework that integrates online disturbance estimation into the planning-control loop for quadrotor flight in narrow space.<n> Experiments demonstrate that a quadrotor with a diagonal length of 0.39m can traverse straight, sloped, and curved tunnels as narrow as 0.6m, outperforming human pilots in both success rate and flight efficiency.
  arXiv  Detail & Related papers  (2026-07-20T01:58:05Z)
• Conflict Resolution under Degraded Surveillance in Air Corridors Using Multi-Agent Reinforcement Learning [0.0]
  This study develops a Deep Q-Network-based Multi-Agent Reinforcement Learning framework for decentralized conflict resolution.<n>The framework supports the simulation-based evaluation of safer AAM conflict-resolution strategies under degraded surveillance conditions.
  arXiv  Detail & Related papers  (2026-07-13T20:11:44Z)
• Pushing the Performance Limits in Autonomous Racing: Continuous Stability-Aware Adaptive Velocity Planning in Formula Student Driverless [1.0499611180329804]
  In autonomous racing, precise planning of the target velocity of a race car is crucial for competitive lap times and stable driving behavior.<n>We present a novel approach to Velocity Planning (VP) that dynamically adapts to changing conditions.<n>Our proposed approach was evaluated on a real Formula Student race car, showing a lap time improvement of 35 % over ten laps and an average increase of 8 % compared to a non-adaptive approach.
  arXiv  Detail & Related papers  (2026-06-09T11:40:30Z)
• Robust Spatiotemporal Motion Planning for Multi-Agent Autonomous Racing via Topological Gap Identification and Accelerated MPC [30.927534234540502]
  Current methods often oversimplify or abandon strict kinematic constraints.<n>We propose a Topological Identification and Accelerated MPC framework.<n>It reduces total maneuver time by 51.6% in sequential scenarios.<n>It consistently maintains an overtaking success rate exceeding 81% in dense bottlenecks.
  arXiv  Detail & Related papers  (2026-03-10T04:55:30Z)
• Spatially-Aware Adaptive Trajectory Optimization with Controller-Guided Feedback for Autonomous Racing [74.83272587893508]
  We present a framework for autonomous raceline optimization that combines NURBS-based trajectory representation, CMA-ES global trajectory optimization, and controller-guided spatial feedback.<n>In simulation, our approach achieves a 17.38% lap time reduction compared to a controller parametrized with maximum static acceleration.<n>On real hardware, tested with different tire compounds ranging from high to low friction, we obtain a 7.60% lap time improvement without explicitly parametrizing friction.
  arXiv  Detail & Related papers  (2026-02-17T15:10:44Z)
• A Tricycle Model to Accurately Control an Autonomous Racecar with Locked Differential [71.53284767149685]
  We present a novel formulation to model the effects of a locked differential on the lateral dynamics of an autonomous open-wheel racecar. We include a micro-steps discretization approach to accurately linearize the dynamics and produce a prediction suitable for real-time implementation.
  arXiv  Detail & Related papers  (2023-12-22T16:29:55Z)
• DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control [62.24301794794304]
  Deep Adaptive Trajectory Tracking (DATT) is a learning-based approach that can precisely track arbitrary, potentially infeasible trajectories in the presence of large disturbances in the real world. DATT significantly outperforms competitive adaptive nonlinear and model predictive controllers for both feasible smooth and infeasible trajectories in unsteady wind fields. It can efficiently run online with an inference time less than 3.2 ms, less than 1/4 of the adaptive nonlinear model predictive control baseline.
  arXiv  Detail & Related papers  (2023-10-13T12:22:31Z)
• Motion Planning and Control for Multi Vehicle Autonomous Racing at High Speeds [100.61456258283245]
  This paper presents a multi-layer motion planning and control architecture for autonomous racing. The proposed solution has been applied on a Dallara AV-21 racecar and tested at oval race tracks achieving lateral accelerations up to 25 $m/s2$.
  arXiv  Detail & Related papers  (2022-07-22T15:16:54Z)
• Robustifying the Deployment of tinyML Models for Autonomous mini-vehicles [61.27933385742613]
  We propose a closed-loop learning flow for autonomous driving mini-vehicles that includes the target environment in-the-loop. We leverage a family of tinyCNNs to control the mini-vehicle, which learn in the target environment by imitating a computer vision algorithm, i.e., the expert. When running the family of CNNs, our solution outperforms any other implementation on the STM32L4 and k64f (Cortex-M4), reducing the latency by over 13x and the energy consummation by 92%.
  arXiv  Detail & Related papers  (2020-07-01T07:54:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.