GSDrive: Reinforcing Driving Policies by Multi-mode Trajectory Probing with 3D Gaussian Splatting Environment

• URL: http://arxiv.org/abs/2604.28111v2
• Date: Fri, 01 May 2026 05:32:26 GMT
• Title: GSDrive: Reinforcing Driving Policies by Multi-mode Trajectory Probing with 3D Gaussian Splatting Environment
• Abstract summary: End-to-end (E2E) autonomous driving presents a promising approach for translating perceptual inputs directly into driving actions.<n>We introduce GSDrive, a framework that exploits 3D Gaussian Splatting (3DGS) for differentiable, physics-based reward shaping in E2E driving policy improvement.
• Score: 6.425301529118419
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: End-to-end (E2E) autonomous driving presents a promising approach for translating perceptual inputs directly into driving actions. However, prohibitive annotation costs and temporal data quality degradation hinder long-term real-world deployment. While combining imitation learning (IL) and reinforcement learning (RL) is a common strategy for policy improvement, conventional RL training relies on delayed, event-based rewards-policies learn only from catastrophic outcomes such as collisions, leading to premature convergence to suboptimal behaviors. To address these limitations, we introduce GSDrive, a framework that exploits 3D Gaussian Splatting (3DGS) for differentiable, physics-based reward shaping in E2E driving policy improvement. Our method incorporates a flow matching-based trajectory predictor within the 3DGS simulator, enabling multi-mode trajectory probing where candidate trajectories are rolled out to assess prospective rewards. This establishes a bidirectional knowledge exchange between IL and RL by grounding reward functions in physically simulated interaction signals, offering immediate dense feedback instead of sparse catastrophic events. Evaluated on the reconstructed nuScenes dataset, our method surpasses existing simulation-based RL driving approaches in closed-loop experiments. Code is available at https://github.com/ZionGo6/GSDrive.

Related papers

• Knowledge-Data-Dual-Driven Reinforcement Learning for Autonomous Vehicle Control in Mixed Traffic [7.833666254318349]
  In mixed traffic, decision-making for autonomous vehicles (AVs) confronts three interrelated challenges.<n>First, physics-based priors fail to capture latent interactive vehicle intentions and diverse driver behaviors.<n>Second, abrupt maneuvers by surrounding vehicles cause non-stationarity, leaving long-tail safety events under-explored.<n>Third, hybrid action spaces destabilize unified RL training due to the different temporal scales of continuous car-following and discrete lane-changing maneuvers.
  arXiv  Detail & Related papers  (2026-08-14T02:07:13Z)
• CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving [66.77752555295355]
  We present CLEAR, a system that enables closed-loop training using Reinforcement Learning (RL) at scale for E2E-AD.<n>We show that with a simple reward, CLEAR significantly outperforms previous methods and sets new state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-07-03T00:34:50Z)
• CausalDrive: Real-time Causal World Models for Autonomous Driving [60.66609721457312]
  We present CausalDrive, a controllable, real-time foundation driving world.<n>CaulDrive operates solely on the initial front-view frame, the ego-vehicle's trajectory, and a macroscopic text prompt.<n>We demonstrate its versatility across three downstream applications: (1) generative closed-loop evaluation with significantly mitigated collision artifacts, (2) large-scale Reinforcement Learning (RL) post-training driven by a Video2Reward module, and (3) real-time human-in-the-loop simulation.
  arXiv  Detail & Related papers  (2026-06-13T15:04:44Z)
• MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving [62.43744546817599]
  Vision-language--action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings.<n>We propose MAPLE, a novel framework for reactive, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model.<n> MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.
  arXiv  Detail & Related papers  (2026-05-13T23:35:14Z)
• Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing [73.88859384645264]
  Out-Of-Distribution (OOD) generalization to various racetracks utilizes Machine Learning (ML) to encode the mathematical relation between sensor data and vehicle actuation for end-to-end control.<n>This paper presents a DRL method that parameterizes nonlinear vehicle dynamics from the spectral distribution of depth measurements with a non-geometric, physics-informed reward, to infer vehicle time-optimal and overtaking racing controls with an Artificial Neural Network (ANN)<n>The policy outperforms human demonstrations by 12% in OOD tracks on proportionally scaled hardware, by maximizing the friction circle with tire dynamics that resemble an empirical Pacejka tire model.
  arXiv  Detail & Related papers  (2026-04-10T17:12:07Z)
• PerlAD: Towards Enhanced Closed-loop End-to-end Autonomous Driving with Pseudo-simulation-based Reinforcement Learning [23.599241673009956]
  We present a novel Pseudo-simulation-based RL method for closed-loop end-to-end autonomous driving, PerlAD.<n>Based on offline datasets, PerlAD constructs a pseudo-simulation that operates in vector space, enabling efficient, rendering-free trial-and-error training.<n> PerlAD achieves state-of-the-art performance on the Bench2Drive benchmark, surpassing the previous E2E RL method by 10.29% in Driving Score.
  arXiv  Detail & Related papers  (2026-03-16T07:09:07Z)
• Offline Reinforcement Learning for End-to-End Autonomous Driving [1.2891210250935148]
  End-to-end (E2E) autonomous driving models take only camera images as input and directly predict a future trajectory.<n>Online reinforcement learning (RL) could mitigate IL-induced issues.<n>We introduce a camera-only E2E offline RL framework that performs no additional exploration and trains solely on a fixed simulator dataset.
  arXiv  Detail & Related papers  (2025-12-21T09:21:04Z)
• ZTRS: Zero-Imitation End-to-end Autonomous Driving with Trajectory Scoring [52.195295396336526]
  ZTRS (Zero-Imitation End-to-End Autonomous Driving with Trajectory Scoring) is a framework that combines the strengths of both worlds: sensor inputs without losing information and RL training for robust planning.<n>ZTRS demonstrates strong performance across three benchmarks: Navtest, Navhard, and HUGSIM.
  arXiv  Detail & Related papers  (2025-10-28T06:26:36Z)
• RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning [54.52545900359868]
  We propose RAD, a 3DGS-based closed-loop Reinforcement Learning framework for end-to-end Autonomous Driving.<n>To enhance safety, we design specialized rewards to guide the policy in effectively responding to safety-critical events and understanding real-world causal relationships.<n>Compared to IL-based methods, RAD achieves stronger performance in most closed-loop metrics, particularly exhibiting a 3x lower collision rate.
  arXiv  Detail & Related papers  (2025-02-18T18:59:21Z)
• Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model [63.336123527432136]
  We introduce Bench2Drive-R, a generative framework that enables reactive closed-loop evaluation.<n>Unlike existing video generative models for autonomous driving, the proposed designs are tailored for interactive simulation.<n>We compare the generation quality of Bench2Drive-R with existing generative models and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-11T06:35:18Z)
• Autonomous Vehicle Controllers From End-to-End Differentiable Simulation [57.278726604424556]
  We propose a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers.<n>Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of environment dynamics serve as a useful prior to help the agent learn a more grounded policy.<n>We find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.
  arXiv  Detail & Related papers  (2024-09-12T11:50:06Z)
• Integrating Deep Reinforcement Learning with Model-based Path Planners for Automated Driving [0.0]
  We propose a hybrid approach for integrating a path planning pipe into a vision based DRL framework. In summary, the DRL agent is trained to follow the path planner's waypoints as close as possible. Experimental results show that the proposed method can plan its path and navigate between randomly chosen origin-destination points.
  arXiv  Detail & Related papers  (2020-02-02T17:10:19Z)

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.