# PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2310.13295 · HTML: https://mlsanity.com/paper/2310.13295/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 20 Oct 2023.

## Builds on (most cited first, 13 of 13)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation](https://mlsanity.com/paper/1703.00420/) (2017)
- [Neural probabilistic motor primitives for humanoid control](https://mlsanity.com/paper/1811.11711/) (2018)
- [PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning](https://mlsanity.com/paper/1710.03937/) (2017)
- [Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey](https://mlsanity.com/paper/2011.13112/) (2020)
- [DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles](https://mlsanity.com/paper/2301.06512/) (2023)
- [Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors](https://mlsanity.com/paper/2305.04412/) (2023)
- [Variational End-to-End Navigation and Localization](https://mlsanity.com/paper/1811.10119/) (2018)
- [Crowd-Aware Robot Navigation for Pedestrians with Multiple Collision Avoidance Strategies via Map-based Deep Reinforcement Learning](https://mlsanity.com/paper/2109.02541/) (2021)
- [Learning to Socially Navigate in Pedestrian-rich Environments with Interaction Capacity](https://mlsanity.com/paper/2203.16154/) (2022)
- [PFilter: Building Persistent Maps through Feature Filtering for Fast and Accurate LiDAR-based SLAM](https://mlsanity.com/paper/2208.14848/) (2022)
- [Towards navigation without precise localization: Weakly supervised learning of goal-directed navigation cost map](https://mlsanity.com/paper/1906.02468/) (2019)
- [Robot Navigation with Reinforcement Learned Path Generation and Fine-Tuned Motion Control](https://mlsanity.com/paper/2210.10639/) (2022)

## Built on by (most cited first, 7 of 7)

- [LDP: A Local Diffusion Planner for Efficient Robot Navigation and Collision Avoidance](https://mlsanity.com/paper/2407.01950/) (2024)
- [Perception Helps Planning: Facilitating Multi-Stage Lane-Level Integration via Double-Edge Structures](https://mlsanity.com/paper/2407.11644/) (2024)
- [RUMOR: Reinforcement learning for Understanding a Model of the Real World for Navigation in Dynamic Environments](https://mlsanity.com/paper/2404.16672/) (2024)
- [LFP: Efficient and Accurate End-to-End Lane-Level Planning via Camera-LiDAR Fusion](https://mlsanity.com/paper/2409.14170/) (2024)
- [ColorDynamic: Generalizable, Scalable, Real-time, End-to-end Local Planner for Unstructured and Dynamic Environments](https://mlsanity.com/paper/2502.19892/) (2025)
- [Decision Transformer-Based Drone Trajectory Planning with Dynamic Safety-Efficiency Trade-Offs](https://mlsanity.com/paper/2507.21506/) (2025)
- [ContactRL: Safe Reinforcement Learning based Motion Planning for Contact based Human Robot Collaboration](https://mlsanity.com/paper/2512.03707/) (2025)

## Abstract (arXiv)

Robot navigation using deep reinforcement learning (DRL) has shown great potential in improving the performance of mobile robots. Nevertheless, most existing DRL-based navigation methods primarily focus on training a policy that directly commands the robot with low-level controls, like linear and angular velocities, which leads to unstable speeds and unsmooth trajectories of the robot during the long-term execution. An alternative method is to train a DRL policy that outputs the navigation path directly. However, two roadblocks arise for training a DRL policy that outputs paths: (1) The action space for potential paths often involves higher dimensions comparing to low-level commands, which increases the difficulties of training; (2) It takes multiple time steps to track a path instead of a single time step, which requires the path to predicate the interactions of the robot w.r.t. the dynamic environment in multiple time steps. This, in turn, amplifies the challenges associated with training. In response to these challenges, we propose PathRL, a novel DRL method that trains the policy to generate the navigation path for the robot. Specifically, we employ specific action space discretization techniques and tailored state space representation methods to address the associated challenges. In our experiments, PathRL achieves better success rates and reduces angular rotation variability compared to other DRL navigation methods, facilitating stable and smooth robot movement. We demonstrate the competitive edge of PathRL in both real-world scenarios and multiple challenging simulation environments.