ParkingWorld: End-to-End Autonomous Parking Reinforcement Learning from Corrective Experience in 3DGS Simulation

• URL: http://arxiv.org/abs/2605.25029v2
• Date: Tue, 26 May 2026 07:39:20 GMT
• Title: ParkingWorld: End-to-End Autonomous Parking Reinforcement Learning from Corrective Experience in 3DGS Simulation
• Abstract summary: This paper presents a correction-in-the-loop sample-efficient reinforcement learning framework for end-to-end autonomous parking.<n>It is entirely trained in a photorealistic 3D Gaussian Splatting (3DGS) parking simulator that enables high-fidelity digital reconstruction of real-world scenes.<n>Our method achieves substantial improvements in parking success rate, operational efficiency, and safety performance across diverse scenarios.
• Score: 10.525967236174223
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous parking demands precise low-speed maneuvering within narrow, cluttered, and highly constrained environments, where vehicles must navigate tight spaces while avoiding static obstacles and complex geometric boundaries. Unlike imitation learning, which typically requires massive volumes of high-quality expert demonstrations to converge to a stable policy and often suffers from limited generalization to unseen scenarios, traditional reinforcement learning (RL) methods face persistent challenges including excessive training overhead, inefficient exploration, and even failure to learn viable parking strategies in challenging settings. To address these limitations, this paper presents a correction-in-the-loop sample-efficient reinforcement learning (CIL-SERL) framework for end-to-end autonomous parking, which is entirely trained in a photorealistic 3D Gaussian Splatting (3DGS) parking simulator that enables high-fidelity digital reconstruction of real-world scenes. Inspired by error-correction notebooks used in learning practice, we design a novel multi-level replay buffer mechanism. These buffers hierarchically organize and store standard RL rollouts, human corrective interventions, failed exploration trajectories, and rollback-based correction segments in separate yet interconnected memory regions, facilitating structured sampling and targeted learning during training. The proposed framework is systematically evaluated in both the 3DGS simulation environment and a physical vehicle platform. Extensive experimental results demonstrate that our method achieves substantial improvements in parking success rate, operational efficiency, and safety performance across diverse scenarios, validating the effectiveness and practical applicability of the proposed CIL-SERL-based end-to-end autonomous parking solution.

Related papers

• Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform [6.737714968545043]
  A key challenge in modern robotics is to adapt to changing environments.<n>In particular, learning to drive on a new track-floor combination with the least amount of new experience naturally frames a continual learning problem.<n>This work proposes a continual RL framework based on Continual Backpropagation that is able to train a generalistic policy on a set of tracks and then fine- tune it within 15 minutes to outperform classical controllers.
  arXiv  Detail & Related papers  (2026-07-27T12:01:29Z)
• ParkingTransformer: LLM-Enhanced End-to-End Trajectory Planning for Autonomous Parking [13.901233386612722]
  ParkingTransformer is a novel framework that leverages multi-view perception and the scene understanding capability of Large Language Models (LLMs)<n>To compensate for the inadequate spatial reasoning ability of LLMs, we introduce 3D positional encoding to explicitly inject spatial geometric awareness.<n>Our method achieves a driving score of 61.32 in CARLA simulator and an average success rate of 88.70% in real-world experiments.
  arXiv  Detail & Related papers  (2026-06-12T05:52:01Z)
• 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)
• REAP: Reinforcement-Learning End-to-End Autonomous Parking with Gaussian Splatting Simulator for Real2Sim2Real Transfer [15.536851529885922]
  We propose a Reinforcement learning End-to-end Autonomous Parking method (REAP)<n>REAP employs Soft Actor-Critic (SAC) within an asymmetric reinforcement learning framework to improve training efficiency and inference performance.<n>To ensure that the trained reinforcement learning network can directly transfer to real-world scenarios, we have established a Real2Sim2Real simulator.
  arXiv  Detail & Related papers  (2026-05-09T05:50:40Z)
• SunnyParking: Multi-Shot Trajectory Generation and Motion State Awareness for Human-like Parking [24.480545421791234]
  We propose a novel dual-branch E2E architecture that achieves motion state awareness by jointly predicting spatial trajectories and discrete motion state sequences.<n> Experimental results demonstrate that our framework generates more robust and human-like trajectories in complex multi-shot parking scenarios.<n>We open-source a new parking dataset of the CARLA simulator, specifically designed to evaluate full prediction capabilities under complex maneuvers.
  arXiv  Detail & Related papers  (2026-02-25T08:35:58Z)
• Adapting Reinforcement Learning for Path Planning in Constrained Parking Scenarios [6.734318562862061]
  We introduce a Deep Reinforcement Learning framework for real-time path planning in parking scenarios.<n>Unlike classical planners, our solution does not require ideal and structured perception.<n>At test time, the policy generates actions through a single forward pass at each step, which is lightweight enough for real-time deployment.
  arXiv  Detail & Related papers  (2026-01-30T04:35:49Z)
• Scaling Rough Terrain Locomotion with Automatic Curriculum Reinforcement Learning [16.89722808439415]
  We propose a Learning Progress-based Automatic Curriculum Reinforcement Learning framework.<n>It estimates the agent's learning progress online and adaptively adjusts the task-sampling distribution.<n>It enables automatic curriculum generation without prior knowledge of the difficulty distribution over the task space.
  arXiv  Detail & Related papers  (2026-01-24T11:54:16Z)
• A Curriculum-Based Deep Reinforcement Learning Framework for the Electric Vehicle Routing Problem [0.4666493857924357]
  Electric vehicle routing problem with time windows (EVRPTW) is a complex optimization problem in sustainable logistics.<n>We propose a curriculum-based deep reinforcement learning (CB-DRL) framework designed to resolve this instability.
  arXiv  Detail & Related papers  (2026-01-21T14:42:33Z)
• Optimization-Guided Diffusion for Interactive Scene Generation [52.23368750264419]
  We present OMEGA, an optimization-guided, training-free framework that enforces structural consistency and interaction awareness during diffusion-based sampling.<n>We show that OMEGA improves generation realism, consistency, and controllability, increasing the ratio of physically and behaviorally valid scenes.<n>Our approach can also generate $5times$ more near-collision frames with a time-to-collision under three seconds.
  arXiv  Detail & Related papers  (2025-12-08T15:56:18Z)
• A General Infrastructure and Workflow for Quadrotor Deep Reinforcement Learning and Reality Deployment [48.90852123901697]
  We propose a platform that enables seamless transfer of end-to-end deep reinforcement learning (DRL) policies to quadrotors.<n>Our platform provides rich types of environments including hovering, dynamic obstacle avoidance, trajectory tracking, balloon hitting, and planning in unknown environments.
  arXiv  Detail & Related papers  (2025-04-21T14:25:23Z)
• 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)
• ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable [88.08120417169971]
  Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data. This work explores generating safety-critical driving scenarios by modifying complex real-world regular scenarios through trajectory optimization. Our approach addresses unrealistic diverging trajectories and unavoidable collision scenarios that are not useful for training robust planner.
  arXiv  Detail & Related papers  (2024-09-12T08:26:33Z)
• Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Driving [100.57791628642624]
  We introduce a safety guaranteed learning framework for vision-based end-to-end autonomous driving. We design a learning system equipped with differentiable control barrier functions (dCBFs) that is trained end-to-end by gradient descent.
  arXiv  Detail & Related papers  (2022-03-04T16:14:33Z)

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.