Ren XIN

Persist in doing what is difficult but right.

I received my Ph.D. degree in Robotics and Automation Systems from the Hong Kong University of Science and Technology (HKUST), under the supervision of Prof. Jun Ma.

My primary research field is learning-based planning and control for autonomous driving. I also have some experience on 3D reconstruction, traditional optimization/sampling based planning methods and CUDA programming in projects.

As to my educational background, I hold an M.Sc. degree from the Hong Kong University of Science and Technology (HKUST) and a Bachelor degree from the Ocean University of China (OUC).

I aim to leverage my expertise in mechanical engineering and artificial intelligence to break the technology boundaries of intelligent systems, introducing technology to the masses.

Served as reviewer for TITS，RAL, ICML, IROS, and ICRA.

news

Oct 23, 2024	Make this page online!

selected publications

NetRoller: Interfacing General and Specialized Models for End-to-End Autonomous Driving

Ren Xin, Hongji Liu, Xiaodong Mei, Wenru Liu, Maosheng Ye, and 2 more authors

IEEE Transactions on Vehicular Technology, 2025

Abs arXiv Bib Code

Integrating General Models (GMs) such as Large Language Models (LLMs), with Specialized Models (SMs) in autonomous driving tasks presents a promising approach to mitigating challenges in data diversity and model capacity of existing specialized driving models. However, this integration leads to problems of asynchronous systems, which arise from the distinct characteristics inherent in GMs and SMs. To tackle this challenge, we propose NetRoller, an adapter that incorporates a set of novel mechanisms to facilitate the seamless integration of GMs and specialized driving models. Specifically, our mechanisms for interfacing the asynchronous GMs and SMs are organized into three key stages. NetRoller first harvests semantically rich and computationally efficient representations from the reasoning processes of LLMs using an early stopping mechanism, which preserves critical insights on driving context while maintaining low overhead. It then applies learnable query embeddings, nonsensical embeddings, and positional layer embeddings to facilitate robust and efficient cross-modality translation. At last, it employs computationally efficient Query Shift and Feature Shift mechanisms to enhance the performance of SMs through few-epoch fine-tuning. Based on the mechanisms formalized in these three stages, NetRoller enables specialized driving models to operate at their native frequencies while maintaining situational awareness of the GM. Experiments conducted on the nuScenes dataset demonstrate that integrating GM through NetRoller significantly improves human similarity and safety in planning tasks, and it also achieves noticeable precision improvements in detection and mapping tasks for end-to-end autonomous driving.
@article{xin2024generictrajectoryplanningmethod, title = {NetRoller: Interfacing General and Specialized Models for End-to-End Autonomous Driving}, author = {Xin, Ren and Liu, Hongji and Mei, Xiaodong and Liu, Wenru and Ye, Maosheng and Chen, Zhili and Ma, Jun}, journal = {IEEE Transactions on Vehicular Technology}, year = {2025}, eprint = {2506.14589}, archiveprefix = {arXiv}, primaryclass = {cs.RO}, url = {https://arxiv.org/abs/2506.14589}, }
PlanScope: Learning to Plan Within Decision Scope Does Matter

Ren Xin, Jie Cheng, Hongji Liu, and Jun Ma

IEEE Robotics and Automation Letters, 2025

Abs arXiv Bib Code Website

In the context of autonomous driving, learning-based methods have been promising for the development of planning modules. During the training process of planning modules, directly minimizing the discrepancy between expert-driving logs and planning output is widely deployed. In general, driving logs consist of suddenly appearing obstacles or swiftly changing traffic signals, which typically necessitate swift and nuanced adjustments in driving maneuvers. Concurrently, future trajectories of the vehicles exhibit their long-term decisions, such as adhering to a reference lane or circumventing stationary obstacles. Due to the unpredictable influence of future events in driving logs, reasoning bias could be naturally introduced to learning based planning modules, which leads to a possible degradation of driving performance. To address this issue, we identify the decisions and their corresponding time horizons, and characterize a so-called decision scope by retaining decisions within derivable horizons only, to mitigate the effect of irrational behaviors caused by unpredictable events. Several viable implementations have been proposed, among which batch normalization along the temporal dimension is particularly effective and achieves superior performance. It consistently outperforms baseline methods in terms of driving scores, as demonstrated through closed-loop evaluations on the nuPlan dataset. Essentially, this approach accommodates an plug-and-play feature to enhance the closed-loop performance of other learning-based planning models.
@article{xin2024generictrajectoryplanningmethoe, title = {PlanScope: Learning to Plan Within Decision Scope Does Matter}, author = {Xin, Ren and Cheng, Jie and Liu, Hongji and Ma, Jun}, year = {2025}, journal = {IEEE Robotics and Automation Letters}, eprint = {2411.00476}, archiveprefix = {arXiv}, primaryclass = {cs.RO}, url = {https://arxiv.org/abs/2411.00476}, }
A Generic Trajectory Planning Method for Constrained All-Wheel-Steering Robots

Ren Xin, Hongji Liu, Yingbing Chen, Jie Cheng, Sheng Wang, and 2 more authors

In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024

Abs arXiv Bib Code Website

This paper presents a generic trajectory planning method for constrained all-wheel-steering robots. The proposed method is based on the concept of the velocity field, which is a novel representation of the traveling cost in the robot’s workspace. The velocity field is defined as a vector field that assigns a velocity vector to each point in the workspace, representing the optimal velocity for the robot to reach that point. The velocity field is computed using a novel iterative method that takes into account the robot’s kinematic constraints and the obstacles in the workspace. The trajectory planning problem is then formulated as a path optimization problem, where the goal is to find a path that minimizes the integral of the velocity field along the path. The proposed method is evaluated in simulation and on a real robot, and the results show that it can generate smooth and collision-free trajectories for all-wheel-steering robots in complex environments.
@inproceedings{xin2024generictrajectoryplanningmethof, title = {A Generic Trajectory Planning Method for Constrained All-Wheel-Steering Robots}, author = {Xin, Ren and Liu, Hongji and Chen, Yingbing and Cheng, Jie and Wang, Sheng and Ma, Jun and Liu, Ming}, booktitle = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems}, year = {2024}, eprint = {2404.09677}, archiveprefix = {arXiv}, primaryclass = {cs.RO}, url = {https://arxiv.org/abs/2404.09677}, note = {} }

RiskMap: A Unified Driving Context Representation for Autonomous Motion Planning in Urban Driving Environment

Ren Xin, Sheng Wang, Yingbing Chen, Jie Cheng, Ming Liu, and 1 more author

In Proceedings of the IEEE International Conference on Robotics and Biomimetics, 2024

arXiv Bib Blog Code

@inproceedings{xin2024riskmapunifieddrivingcontext,
  title = {{RiskMap:} A Unified Driving Context Representation for Autonomous Motion Planning in Urban Driving Environment},
  author = {Xin, Ren and Wang, Sheng and Chen, Yingbing and Cheng, Jie and Liu, Ming and Ma, Jun},
  booktitle = {Proceedings of the IEEE International Conference on Robotics and Biomimetics},
  year = {2024},
  eprint = {2406.04451},
  archiveprefix = {arXiv},
  primaryclass = {cs.RO},
  url = {https://arxiv.org/abs/2406.04451},
}

Velocity Field: An Informative Traveling Cost Representation for Trajectory Planning

Ren Xin, Jie Cheng, Sheng Wang, and Ming Liu

In Proceedings of the IEEE International Conference on Robotics and Biomimetics, 2023

DOI arXiv Bib Blog Code

@inproceedings{10355004,
  author = {Xin, Ren and Cheng, Jie and Wang, Sheng and Liu, Ming},
  title = {{Velocity Field:} An Informative Traveling Cost Representation for Trajectory Planning},
  booktitle = {Proceedings of the IEEE International Conference on Robotics and Biomimetics},
  year = {2023},
  volume = {},
  number = {},
  pages = {1-6},
  keywords = {Costs;Trajectory planning;Planning;Trajectory;Iterative methods;Reliability;Task analysis},
  doi = {10.1109/ROBIO58561.2023.10355004},
}

FCUS: Traffic Rule-Aware Vehicle Trajectory Forecasting Using Continuous Unlikelihood and Signal Temporal Logic Feature

Sheng Wang, Ren Xin, Jie Cheng, Xiaodong Mei, and Ming Liu

In Proceedings of the IEEE International Conference on Robotics and Biomimetics, 2023

DOI Bib Website

@inproceedings{10354968,
  author = {Wang, Sheng and Xin, Ren and Cheng, Jie and Mei, Xiaodong and Liu, Ming},
  title = {{FCUS:} Traffic Rule-Aware Vehicle Trajectory Forecasting Using Continuous Unlikelihood and Signal Temporal Logic Feature},
  booktitle = {Proceedings of the IEEE International Conference on Robotics and Biomimetics},
  year = {2023},
  volume = {},
  number = {},
  pages = {1-6},
  keywords = {Biological system modeling;Neural networks;Predictive models;Trajectory;Safety;Forecasting;Task analysis},
  doi = {10.1109/ROBIO58561.2023.10354968},
}

Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictions

Sheng Wang, Yingbing Chen, Jie Cheng, Xiaodong Mei, Ren Xin, and 2 more authors

In Proceedings of the IEEE International Conference on Robotics and Automation, 2024

DOI Bib

@inproceedings{10610154,
  author = {Wang, Sheng and Chen, Yingbing and Cheng, Jie and Mei, Xiaodong and Xin, Ren and Song, Yongkang and Liu, Ming},
  booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation},
  title = {Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictions},
  year = {2024},
  volume = {},
  number = {},
  pages = {14450-14456},
  keywords = {Accuracy;Roads;Self-supervised learning;Predictive models;Trajectory;History;Task analysis},
  doi = {10.1109/ICRA57147.2024.10610154},
}

Real-Time Metric-Semantic Mapping for Autonomous Navigation in Outdoor Environments

Jianhao Jiao, Ruoyu Geng, Yuanhang Li, Ren Xin, Bowen Yang, and 5 more authors

IEEE Transactions on Automation Science and Engineering, 2024

DOI Bib Website

@article{10620438,
  author = {Jiao, Jianhao and Geng, Ruoyu and Li, Yuanhang and Xin, Ren and Yang, Bowen and Wu, Jin and Wang, Lujia and Liu, Ming and Fan, Rui and Kanoulas, Dimitrios},
  journal = {IEEE Transactions on Automation Science and Engineering},
  title = {Real-Time Metric-Semantic Mapping for Autonomous Navigation in Outdoor Environments},
  year = {2024},
  volume = {},
  number = {},
  pages = {1-12},
  keywords = {Semantics;Navigation;Robots;Robot sensing systems;Sensors;Real-time systems;Location awareness;Autonomous driving;mapping;navigation},
  doi = {10.1109/TASE.2024.3429280},
}

MPNP: Multi-Policy Neural Planner for Urban Driving

Jie Cheng, Ren Xin, Sheng Wang, and Ming Liu

In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022

DOI Bib Website

@inproceedings{9982111,
  author = {Cheng, Jie and Xin, Ren and Wang, Sheng and Liu, Ming},
  booktitle = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems},
  title = {MPNP: Multi-Policy Neural Planner for Urban Driving},
  year = {2022},
  volume = {},
  number = {},
  pages = {10549-10554},
  keywords = {Force;Data models;Behavioral sciences;Trajectory;Planning;Intelligent robots},
  doi = {10.1109/IROS47612.2022.9982111},
}

Efficient Speed Planning for Autonomous Driving in Dynamic Environment With Interaction Point Model

Yingbing Chen, Ren Xin, Jie Cheng, Qingwen Zhang, Xiaodong Mei, and 2 more authors

IEEE Robotics and Automation Letters, 2022

DOI Bib Website

@article{9894671,
  author = {Chen, Yingbing and Xin, Ren and Cheng, Jie and Zhang, Qingwen and Mei, Xiaodong and Liu, Ming and Wang, Lujia},
  journal = {IEEE Robotics and Automation Letters},
  title = {Efficient Speed Planning for Autonomous Driving in Dynamic Environment With Interaction Point Model},
  year = {2022},
  volume = {7},
  number = {4},
  pages = {11839-11846},
  keywords = {Planning;Trajectory;Computational modeling;Autonomous vehicles;Analytical models;Robots;Behavioral sciences;Autonomous vehicle navigation;integrated planning and learning;motion and path planning},
  doi = {10.1109/LRA.2022.3207555},
}

MMFN: Multi-Modal-Fusion-Net for End-to-End Driving

Qingwen Zhang, Mingkai Tang, Ruoyu Geng, Feiyi Chen, Ren Xin, and 1 more author

In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022

DOI Bib

@inproceedings{9981775,
  author = {Zhang, Qingwen and Tang, Mingkai and Geng, Ruoyu and Chen, Feiyi and Xin, Ren and Wang, Lujia},
  booktitle = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems},
  title = {MMFN: Multi-Modal-Fusion-Net for End-to-End Driving},
  year = {2022},
  volume = {},
  number = {},
  pages = {8638-8643},
  keywords = {Point cloud compression;Laser radar;Three-dimensional displays;Navigation;Robot vision systems;Radar imaging;Feature extraction},
  doi = {10.1109/IROS47612.2022.9981775},
}