Jianye Xu

Ph.D. Student · RWTH Aachen University

Jianye Xu

Hello! I’m Jianye, a Ph.D. student at the Chair of Embedded Software (Informatik 11), RWTH Aachen University, supervised by Prof. Bassam Alrifaee.

I study learning- and optimization-based multi-agent decision-making for connected and automated vehicles. I am particularly interested in the interplay between reinforcement learning and control barrier functions.

EmailCVGoogle ScholarGitHubLinkedIn
Jianye Xu
Aachen, Germany

News

Show all news

Research / Publications

Google Scholar

My research connects multi-agent reinforcement learning, optimal control, and connected and automated vehicles, from decision-making in simulation to safe robotic systems.

★ Selected work · Papers listed by year, newest first.

13 publications

Comparison of high-order and truncated Taylor control barrier functions

★TTCBF: A Truncated Taylor Control Barrier Function for High-Order Safety Constraints

Jianye Xu, Bassam Alrifaee

arXiv preprint arXiv:2601.15196 · 2026

Safe Control
PaperCode
BibTeX
@article{xu2026ttcbf,
 archiveprefix = {arXiv},
 author = {Xu, Jianye and Alrifaee, Bassam},
 doi = {10.48550/arXiv.2601.15196},
 eprint = {2601.15196},
 journal = {arXiv preprint arXiv:2601.15196},
 primaryclass = {eess},
 publisher = {arXiv},
 title = {TTCBF: A Truncated Taylor Control Barrier Function for High-Order Safety Constraints},
 year = {2026}
}
Download .bib
About this paper

High-Order Control Barrier Functions (HOCBFs) handle safety constraints with relative degree greater than one by introducing a chain of auxiliary functions. This requires multiple class K functions, whose number and tuning burden grow with the relative degree. Because their parameters affect the conservatism and feasibility of the resulting control constraint, tuning them can complicate controller design. We introduce a Truncated Taylor Control Barrier Function (TTCBF), which extends the discrete-time CBF formulation to high-order safety constraints using a single class K function, independent of relative degree. We also propose an adaptive variant, aTTCBF, which optimizes the class K gain online. This paper updates our earlier TTCBF preprint, which remains available at its original arXiv record.

atZero-shot learning in the CPM Lab2026

Zero-Shot MARL Benchmark in the Cyber-Physical Mobility Lab

Julius Beerwerth, Jianye Xu, Simon Schäfer, Fynn Belderink, Bassam Alrifaee

at - Automatisierungstechnik · 2026

MARLCAVsRobotics
PaperPublisher
BibTeX
@article{beerwerth2026zeroshot,
 author = {Beerwerth, Julius and Xu, Jianye and Schäfer, Simon and Belderink, Fynn and Alrifaee, Bassam},
 copyright = {De Gruyter expressly reserves the right to use all content for commercial text and data mining within the meaning of Section 44b of the German Copyright Act.},
 doi = {10.1515/auto-2025-0057},
 journal = {at - Automatisierungstechnik},
 number = {5},
 pages = {376--385},
 publisher = {De Gruyter},
 title = {Zero-Shot MARL Benchmark in the Cyber-Physical Mobility Lab},
 volume = {74},
 year = {2026}
}
Download .bib
ITSCBeyond safety filtering2026

★Beyond Safety Filtering: Control Barrier Function-Informed Reinforcement Learning for Connected and Automated Vehicles

Jianye Xu, Bassam Alrifaee

2026 IEEE 29th International Conference on Intelligent Transportation Systems (ITSC), in Press · 2026

Safe ControlCAVsRobotics
PaperCode
BibTeX
@inproceedings{xu2026safety,
 author = {Xu, Jianye and Alrifaee, Bassam},
 booktitle = {2026 IEEE 29th International Conference on Intelligent Transportation Systems (ITSC), in Press},
 title = {Beyond Safety Filtering: Control Barrier Function-Informed Reinforcement Learning for Connected and Automated Vehicles},
 year = {2026}
}
Download .bib
ITSMTestbeds: challenges & a roadmap2026

★Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms: Challenges and a Roadmap

Jianye Xu, Johannes Betz, Armin Mokhtarian, Archak Mittal, Mengchi Cai, Rahul Mangharam, Omar M. Shehata, Catherine M. Elias, Jan-Nico Zaech, Patrick Scheffe, Felix Jahncke, Sangeet Sankaramangalam Ulhas, Kaj Munhoz Arfvidsson, Bassam Alrifaee

IEEE Intelligent Transportation Systems Magazine · 2026

CAVsRobotics
PaperPublisher
BibTeX
@article{xu2026smallscale,
 author = {Xu, Jianye and Betz, Johannes and Mokhtarian, Armin and Mittal, Archak and Cai, Mengchi and Mangharam, Rahul and Shehata, Omar M. and Elias, Catherine M. and Zaech, Jan-Nico and Scheffe, Patrick and Jahncke, Felix and Ulhas, Sangeet Sankaramangalam and Arfvidsson, Kaj Munhoz and Alrifaee, Bassam},
 doi = {10.1109/MITS.2026.3666681},
 journal = {IEEE Intelligent Transportation Systems Magazine},
 pages = {2--16},
 title = {Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms: Challenges and a Roadmap},
 year = {2026}
}
Download .bib
About this paper

This paper summarizes the outcomes of the 1st Workshop on Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms at IEEE IV 2024. Small-scale testbeds combine rapid prototyping with experiments that approximate real-world conditions more closely than simulations.

High-order control barrier function parameter and trajectory comparisons

High-Order Control Barrier Functions: Insights and a Truncated Taylor-Based Formulation

Jianye Xu, Bassam Alrifaee

arXiv preprint arXiv:2503.15014 · 2025

Earlier preprint; see the updated TTCBF paper (2026).

Safe Control
Paper
BibTeX
@article{xu2025highorder,
 archiveprefix = {arXiv},
 author = {Xu, Jianye and Alrifaee, Bassam},
 doi = {10.48550/arXiv.2503.15014},
 eprint = {2503.15014},
 journal = {arXiv preprint arXiv:2503.15014},
 primaryclass = {eess},
 publisher = {arXiv},
 title = {High-Order Control Barrier Functions: Insights and a Truncated Taylor-Based Formulation},
 year = {2025}
}
Download .bib
Overtaking and bypassing comparisons for collision avoidance

★A Learning-Based Control Barrier Function for Car-Like Robots: Toward Less Conservative Collision Avoidance

Jianye Xu, Bassam Alrifaee

2025 European Control Conference (ECC) · 2025

Safe ControlCAVsRobotics
PaperPublisherCode
BibTeX
@inproceedings{xu2025learningbased,
 author = {Xu, Jianye and Alrifaee, Bassam},
 booktitle = {2025 European Control Conference (ECC)},
 doi = {10.23919/ECC65951.2025.11187043},
 pages = {988--995},
 title = {A Learning-Based Control Barrier Function for Car-Like Robots: Toward Less Conservative Collision Avoidance},
 year = {2025}
}
Download .bib
About this paper

We propose a learning-based CBF to reduce conservatism in collision avoidance of car-like robots. Traditional CBFs often use Euclidean distance between robots' centers as safety margin, neglecting headings and simplifying geometries to circles. While this ensures smooth, differentiable safety functions required by CBFs, it can be overly conservative in tight environments. To address this limitation, we design a heading-aware safety margin that accounts for the robots' orientations, enabling a less conservative and more accurate estimation of safe regions. Since the function computing this safety margin is non-differentiable, we approximate it with a neural network to ensure differentiability and facilitate integration with CBFs. We describe how we achieve bounded learning error and incorporate the upper bound into the CBF to provide formal safety guarantees through forward invariance. We show that our CBF is a high-order CBF with relative degree two for a system with two robots whose dynamics are modeled by the nonlinear kinematic bicycle model. Experimental results in overtaking and bypassing scenarios reveal a 33.5 % reduction in conservatism compared to traditional methods, while maintaining safety

ITSCReal-time safety filtering2025

A Real-Time Control Barrier Function-Based Safety Filter for Motion Planning with Arbitrary Road Boundary Constraints

Jianye Xu, Chang Che, Bassam Alrifaee

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC) · 2025

Safe ControlCAVsRobotics
PaperPublisherCode
BibTeX
@inproceedings{xu2025realtime,
 author = {Xu, Jianye and Che, Chang and Alrifaee, Bassam},
 booktitle = {2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)},
 doi = {10.1109/ITSC60802.2025.11423203},
 pages = {2818--2825},
 title = {A Real-Time Control Barrier Function-Based Safety Filter for Motion Planning with Arbitrary Road Boundary Constraints},
 year = {2025}
}
Download .bib
Small-scale vehicle and robot testbeds reviewed in the survey

A Survey on Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms: A Guide for Creating a New Testbed

Armin Mokhtarian, Jianye Xu, Patrick Scheffe, Maximilian Kloock, Simon Schäfer, Heeseung Bang, Viet-Anh Le, Sangeet Ulhas, Johannes Betz, Sean Wilson, Spring Berman, Liam Paull, Amanda Prorok, Bassam Alrifaee

IEEE Robotics & Automation Magazine · 2024

CAVsRobotics
PaperPublisherProject Page
BibTeX
@article{mokhtarian2024survey,
 author = {Mokhtarian, Armin and Xu, Jianye and Scheffe, Patrick and Kloock, Maximilian and Schäfer, Simon and Bang, Heeseung and Le, Viet-Anh and Ulhas, Sangeet and Betz, Johannes and Wilson, Sean and Berman, Spring and Paull, Liam and Prorok, Amanda and Alrifaee, Bassam},
 doi = {10.1109/MRA.2024.3505772},
 journal = {IEEE Robotics & Automation Magazine},
 pages = {2--19},
 title = {A Survey on Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms: A Guide for Creating a New Testbed},
 year = {2024}
}
Download .bib
About this paper

A survey of small-scale testbeds for connected and automated vehicles and robot swarms, with an online comparison of more than 25 existing testbeds.

ECCLearning in the CPM Lab2024

Educational Applications of the Cyber-Physical Mobility Lab: A Summary

Simon Schäfer, Jianye Xu, David Klüner, Armin Mokhtarian, Patrick Scheffel, Bassam Alrifaee

2024 European Control Conference (ECC) · 2024

CAVsRobotics
PaperPublisher
BibTeX
@inproceedings{schafer2024educational,
 author = {Schäfer, Simon and Xu, Jianye and Klüner, David and Mokhtarian, Armin and Scheffel, Patrick and Alrifaee, Bassam},
 booktitle = {2024 European Control Conference (ECC)},
 doi = {10.23919/ECC64448.2024.10591176},
 pages = {2666--2671},
 title = {Educational Applications of the Cyber-Physical Mobility Lab: A Summary},
 year = {2024}
}
Download .bib
ECCSafe trajectory planning2024

Limiting Computation Levels in Prioritized Trajectory Planning with Safety Guarantees

Patrick Scheffe, Jianye Xu, Bassam Alrifaee

2024 European Control Conference (ECC) · 2024

Safe ControlCAVs
PaperPublisher
BibTeX
@inproceedings{scheffe2024limiting,
 author = {Scheffe, Patrick and Xu, Jianye and Alrifaee, Bassam},
 booktitle = {2024 European Control Conference (ECC)},
 doi = {10.23919/ECC64448.2024.10591179},
 pages = {297--304},
 title = {Limiting Computation Levels in Prioritized Trajectory Planning with Safety Guarantees},
 year = {2024}
}
Download .bib
Vehicle trajectories in a testbed, intersection, on-ramp, and roundabout

★SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning

Jianye Xu, Pan Hu, Bassam Alrifaee

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC) · 2024

MARLCAVsRobotics
PaperPublisherCode
BibTeX
@inproceedings{xu2024sigmarl,
 author = {Xu, Jianye and Hu, Pan and Alrifaee, Bassam},
 booktitle = {2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)},
 doi = {10.1109/ITSC58415.2024.10919918},
 pages = {768--775},
 title = {SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning},
 year = {2024}
}
Download .bib
About this paper

Sample efficiency and generalization are two key challenges in MARL. Most RL agents exhibit a limited capacity to generalize, often focusing narrowly on specific scenarios, and are usually evaluated in similar or even the same scenarios seen during training. Various methods have been proposed to address these challenges, including experience replay and regularization. However, how observation design in RL affects sample efficiency and generalization remains an under-explored area. We introduce an open-source, decentralized framework named SigmaRL, designed to enhance both sample efficiency and generalization of MARL for motion planning of CAVs. We address this gap by proposing five strategies to design information-dense observations, focusing on general features that are applicable to most traffic scenarios. We train our RL agents using these strategies on an intersection and evaluate their generalization through numerical experiments across completely unseen traffic scenarios, including a new intersection, an on-ramp, and a roundabout. Incorporating these information-dense observations reduces training times to under one hour on a single CPU, and the evaluation results reveal that our RL agents can effectively zero-shot generalize.

Prioritized agents and their interactions on a road network

XP-MARL: Auxiliary Prioritization in Multi-Agent Reinforcement Learning to Address Non-Stationarity

Jianye Xu, Omar Sobhy, Bassam Alrifaee

arXiv preprint arXiv:2409.11852 · 2024

MARLCAVsRobotics
PaperCode
BibTeX
@article{xu2024xpmarl,
 archiveprefix = {arXiv},
 author = {Xu, Jianye and Sobhy, Omar and Alrifaee, Bassam},
 doi = {10.48550/arXiv.2409.11852},
 eprint = {2409.11852},
 journal = {arXiv preprint arXiv:2409.11852},
 primaryclass = {cs},
 publisher = {arXiv},
 title = {XP-MARL: Auxiliary Prioritization in Multi-Agent Reinforcement Learning to Address Non-Stationarity},
 year = {2024}
}
Download .bib
About this paper

Non-stationarity poses a fundamental challenge in MARL, arising from agents simultaneously learning and altering their policies. This creates a non-stationary environment from the perspective of each individual agent, often leading to suboptimal or even unconverged learning outcomes. We propose an open-source framework named XP-MARL, which augments MARL with auxiliary prioritization to address this challenge in cooperative settings. XP-MARL is 1) founded upon our hypothesis that prioritizing agents and letting higher-priority agents establish their actions first would stabilize the learning process and thus mitigate non-stationarity and 2) enabled by our proposed mechanism called action propagation, where higher-priority agents act first and communicate their actions, providing a more stationary environment for others. Moreover, instead of using a predefined or heuristic priority assignment, XP-MARL learns priority-assignment policies with an auxiliary MARL problem, leading to a joint learning scheme. Experiments in a motion-planning scenario involving CAVs demonstrate that XP-MARL improves the safety of a baseline model by 84.4% and outperforms a state-of-the-art approach, which improves the baseline by only 12.8%

ECCCyber-Physical Mobility Lab2021

Cyber-Physical Mobility Lab: An Open-Source Platform for Networked and Autonomous Vehicles

Maximilian Kloock, Patrick Scheffe, Janis Maczijewski, Alexandru Kampmann, Armin Mokhtarian, Stefan Kowalewski, Bassam Alrifaee

2021 European Control Conference (ECC) · 2021

Related platform paper. Jianye Xu is not listed as an author.

CAVsRobotics
PaperPublisher
BibTeX
@inproceedings{kloock2021cyberphysical,
 author = {Kloock, Maximilian and Scheffe, Patrick and Maczijewski, Janis and Kampmann, Alexandru and Mokhtarian, Armin and Kowalewski, Stefan and Alrifaee, Bassam},
 booktitle = {2021 European Control Conference (ECC)},
 doi = {10.23919/ECC54610.2021.9654986},
 pages = {1937--1944},
 title = {Cyber-Physical Mobility Lab: An Open-Source Platform for Networked and Autonomous Vehicles},
 year = {2021}
}
Download .bib

Education and Experience

Experience

Awards

Talks

Teaching

Control and Perception in Connected and Autonomous Vehicles

Master’s course · RWTH Aachen University

Assistant lecturer, winter terms 2024 and 2025

Course architectureArchitecture of the control and perception teaching laboratory
Supervised theses (20)

Ali Elbadawy (2026). Integrating Barrier Functions into Multi-Agent Social Value Orientation for Unsignalized Intersection (Master's thesis, RWTH Aachen University).

Massimo Marcon (2026). Latent World Models for Motion Planning of Connected and Automated Vehicles (Master's thesis, RWTH Aachen University).

Jiaxin Liu (2026). Mixture of Expert Policies for Decision-Making and Motion Planning in Connected and Automated Vehicles (Master's thesis, RWTH Aachen University).

George Halim (2026). Barrier-Certified Exploration for Real-World Reinforcement Learning in the Cyber-Physical Mobility Lab (Bachelor's thesis, RWTH Aachen University).

Yousef Sayed (2026). A Study of Responsibility Assignment in Control Barrier Function for Connected and Automated Vehicles (Bachelor's thesis, RWTH Aachen University).

Maximilian Petri (2025). Reinforcement Learning for Formula Student Autonomous Racing (Master's thesis, RWTH Aachen University).

Chang Che (2025). Constraint-Enforced Multi-Agent Reinforcement Learning for Safe Motion Planning of Connected and Automated Vehicles (Master's thesis, RWTH Aachen University).

Pan Hu (2025). Situation-Aware Trajectory Planning of Connected and Automated Vehicles with Multi-Policy Reinforcement Learning (Master's thesis, RWTH Aachen University).

Daniel Boules (2025). A Prioritization-Based Approach for Enhanced Stability in Non-Stationary Multi-Agent Reinforcement Learning (Bachelor's thesis, RWTH Aachen University).

Fynn Belderink (2025). Model-Based Receding-Horizon Planning in Multi-Agent Reinforcement Learning (Bachelor's thesis, RWTH Aachen University).

Yunjia Chen (2025). Sensor Fusion-Enhanced Map Matching of Bicycle Routes Using Crowdsourced GPS and IMU Data from Smartphones (Bachelor's thesis, RWTH Aachen University).

Xinyue Cui (2024). Determining the Longitudinal and Lateral Acceleration of a Bicycle Using a Smartphone Mounted on Its Handlebar (Master's thesis, RWTH Aachen University).

Lebo Liang (2024). Safe Multi-Agent Control: Integrating Control Barrier Functions with Reinforcement Learning (Bachelor's thesis, Aachen University of Applied Sciences).

Mohamed Shamekh (2024). Model-Predictive-Control-Based Safe Multi-Agent Reinforcement Learning for Motion Planning (Bachelor's thesis, RWTH Aachen University).

Omar Sobhy (2024). Dealing with Non-Stationarity in Multi-Agent Reinforcement Learning Through Learning-Based Dynamic Prioritization (Bachelor's thesis, RWTH Aachen University).

Xia Yan (2024). Learning-Based Motion Planner for Connected and Automated Vehicles (Master's thesis, RWTH Aachen University).

Xilei Chen (2024). Imitation Learning from Optimization-Based Motion Planners for Connected and Automated Vehicles (Bachelor's thesis, RWTH Aachen University).

Raphael Malig (2024). Investigating the Effect of Discretizing Continuous Action Space in Multi-Agent Reinforcement Learning for Motion Planning (Bachelor's thesis, RWTH Aachen University).

Andreas Pletschko (2024). Leveraging Temporal Dependencies for Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning in Motion Planning (Bachelor's thesis, RWTH Aachen University).

Ruizhang Zhou (2024). AI-Based Generation of Testing Scenarios for Motion Planners on Connected and Automated Vehicles (Master's thesis, RWTH Aachen University).

Supervised seminar works (14)

Summer Semester 2026

Lisa Michèle Schilling. A Survey of Large Language Models for Autonomous Driving (RWTH Aachen University).

Philipp Krütt. Policy Learning and Dataset Generation for Cooperative Driving of Connected and Automated Vehicles at a Roundabout (RWTH Aachen University).

Winter Semester 2025/2026

Alexander Lingmann. Generating Testing Scenarios for Motion Planning of Connected and Automated Vehicles (RWTH Aachen University).

Clemens von Molo. Incorporating Different High-Definition Maps in SigmaRL for Connected and Automated Vehicles (RWTH Aachen University).

Summer Semester 2025

Mats Ploder. Safe Reinforcement Learning with Control Barrier Functions for Autonomous Driving: A Survey (RWTH Aachen University).

Burak Kayabasi. Straßengrenzen bei der Verwendung von Control Barrier Functions für autonomes Fahren: Ein Überblick (RWTH Aachen University).

Winter Semester 2024/2025

Hannes Tettenborn. Survey of Attention Mechanisms in Reinforcement Learning for Motion Planning in Autonomous Driving (RWTH Aachen University).

Julian Büttner. Generating Testing Scenarios for Motion Planning of Connected and Automated Vehicles (RWTH Aachen University).

Lasse Jacob. Implementation of an Image-Based Observation Representation in SigmaRL (RWTH Aachen University).

Summer Semester 2024

Colin Kubon. Investigating the Feasibility of Integrating Lanelet2 into CPM Lab (RWTH Aachen University).

Destay Desin Sahan. A Survey of Safe Reinforcement Learning for Autonomous Vehicles (RWTH Aachen University).

Winter Semester 2023/2024

Jonathan Kock. Implementation of a Multi-Agent Imitation Learning Framework for Connected and Automated Vehicles (RWTH Aachen University).

Nico Nußbaum. Implementation of a Multi-Agent Deep Reinforcement Learning Framework for Connected and Automated Vehicles (RWTH Aachen University).

Zirui Bai. Multi-Agent Deep Reinforcement Learning for Connected and Automated Vehicles: A Review (RWTH Aachen University).

Academic Service