PlanRL: A Trajectory Planning Architecture for Reinforcement Learning-based Driving Experts

• URL: http://arxiv.org/abs/2606.26858v1
• Date: Thu, 25 Jun 2026 10:42:15 GMT
• Title: PlanRL: A Trajectory Planning Architecture for Reinforcement Learning-based Driving Experts
• Abstract summary: Reinforcement learning (RL) has become a prominent framework for developing driving experts in autonomous vehicles.<n>We propose a novel trajectory planning architecture for RL driving experts that integrates an RL policy with a kinematic-based trajectory planner.<n>We evaluate our approach on key CARLA benchmarks, where it significantly outperforms existing control-based RL experts.
• Score: 42.30212481193531
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) has become a prominent framework for developing driving experts in autonomous vehicles. However, most existing RL-based experts are designed to output direct control commands (e.g., throttle, steering), which suffer from a lack of interpretability, high spatial complexity in learning road geometries, and poor compatibility with modern end-to-end planning architectures. To address these limitations, we propose a novel trajectory planning architecture for RL driving experts that integrates an RL policy with a polynomial-based trajectory planner. By employing a Frenet-frame coordinate system, our method simplifies complex road geometries into a curvilinear framework, offering a structured coordinate prior that facilitates policy learning. Furthermore, we incorporate a kinematic feasibility check into the planning stage to ensure that generated trajectories remain within the vehicle's physical limits, effectively mitigating cumulative tracking errors typically found in planning-based systems. We evaluate our approach on key CARLA benchmarks, where it significantly outperforms existing state-of-the-art control-based RL experts. On the CARLA Offline Leaderboard v1 and NoCrash benchmarks, our method improves the driving score by 5% and 11%, respectively, and increases the success rate by 8% and 19%.

Related papers

• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving [51.268878540511054]
  We propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy.<n>We show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM.
  arXiv  Detail & Related papers  (2026-04-04T04:12:47Z)
• PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models [51.43746425777865]
  Large Language Models (LLMs) often lack the capacity to formulate global strategies, leading to error propagation in long-horizon tasks.<n>We propose PILOT, a framework designed to internalize the strategic oversight of large models into intrinsic Latent Guidance.
  arXiv  Detail & Related papers  (2026-01-07T12:38:56Z)
• Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail [85.47497935739936]
  Alpamayo-R1 (AR1) is a vision-language-action model that integrates Chain of Causation reasoning with trajectory planning.<n>We show AR1 achieves 12% improvement in planning accuracy on challenging cases compared to a trajectory-only baseline.<n>We plan to release AR1 models and a subset of the CoC in a future update.
  arXiv  Detail & Related papers  (2025-10-30T01:25:34Z)
• CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-scale Reinforcement Learning in Autonomous Driving [23.7034061448326]
  Trajectory planning is vital for autonomous driving, ensuring safe and efficient navigation in complex environments.<n>In this paper, we introduce textbfCarPlanner, a textbfConsistent textbfauto-textbfregressive textbfPlanner that uses reinforcement learning to generate multi-modal trajectories.
  arXiv  Detail & Related papers  (2025-02-27T09:26:22Z)
• TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning [61.33599727106222]
  TeLL-Drive is a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy.<n>A self-attention mechanism then fuses these strategies with the DRL agent's exploration, accelerating policy convergence and boosting robustness.
  arXiv  Detail & Related papers  (2025-02-03T14:22:03Z)
• Reinforced Imitative Trajectory Planning for Urban Automated Driving [3.2436298824947434]
  This paper proposes a novel RL-based trajectory planning method that integrates RL with imitation learning to enable multi-step planning.<n>A transformer-based Bayesian reward function is developed, providing effective reward signals for RL in urban scenarios.<n>The proposed methods were validated on the large-scale real-world urban automated driving nuPlan dataset.
  arXiv  Detail & Related papers  (2024-10-21T03:04:29Z)
• Let Hybrid A* Path Planner Obey Traffic Rules: A Deep Reinforcement Learning-Based Planning Framework [0.0]
  In this work, we combine low-level algorithms such as the hybrid A* path planning with deep reinforcement learning (DRL) to make high-level decisions. The hybrid A* planner is able to generate a collision-free trajectory to be executed by a model predictive controller (MPC) In addition, the DRL algorithm is able to keep the lane change command consistent within a chosen time-period.
  arXiv  Detail & Related papers  (2024-07-01T12:00:10Z)
• LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning [65.86754998249224]
  We develop a novel hybrid planner that leverages a conventional rule-based planner in conjunction with an LLM-based planner. Our approach navigates complex scenarios which existing planners struggle with, produces well-reasoned outputs while also remaining grounded through working alongside the rule-based approach.
  arXiv  Detail & Related papers  (2023-12-30T02:53:45Z)
• Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control [6.144517901919656]
  Reinforcement learning (RL) promises to achieve control performance superior to classical approaches. Standard RL approaches like soft-actor critic (SAC) require extensive amounts of training data to be collected. We apply recently developed data-efficient deep RL methods to vehicle trajectory control.
  arXiv  Detail & Related papers  (2023-11-30T09:38:59Z)
• Trajectory Planning for Autonomous Vehicles Using Hierarchical Reinforcement Learning [21.500697097095408]
  Planning safe trajectories under uncertain and dynamic conditions makes the autonomous driving problem significantly complex. Current sampling-based methods such as Rapidly Exploring Random Trees (RRTs) are not ideal for this problem because of the high computational cost. We propose a Hierarchical Reinforcement Learning structure combined with a Proportional-Integral-Derivative (PID) controller for trajectory planning.
  arXiv  Detail & Related papers  (2020-11-09T20:49:54Z)

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.