Tracailer: An Efficient Trajectory Planner for Tractor-Trailer Robots in Unstructured Environments

The tractor-trailer robot consists of a drivable tractor and one or more non-drivable trailers connected via hitches. Compared to typical car-like robots, the addition of trailers provides greater transportation capability. However, this also complicates motion planning due to the robot’s com- plex kinematics, high-dimensional state space, and deformable structure. To efficiently plan safe, time-optimal trajectories that adhere to the kinematic constraints of the robot and address the challenges posed by its unique features, this paper introduces a lightweight, compact, and high-order smooth trajectory representation for tractor-trailer robots. Based on it, we design an efficiently solvable spatial-temporal trajectory op- timization problem. To deal with deformable structures, which leads to difficulties in collision avoidance, we fully leverage the collision-free regions of the environment, directly applying deformations to trajectories in continuous space. This approach not requires constructing safe regions from the environment using convex approximations through collision-free seed points before each optimization, avoiding the loss of the solution space, thus reducing the dependency of the optimization on This work was supported by the National Key R&D Program of China under Grant No. 2023YFB4706600, the Zhejiang Provincial Science and Technology Plan Project under Grant No. 2024C01170 and the National Natural Science Foundation of China under Grant No. 62322314. 1State Key Laboratory of Industrial Control Technology, Zhejiang Uni- versity, Hangzhou 310027, China. Corresponding author: Fei Gao 2Huzhou Institute of Zhejiang University, Huzhou 313000, China. E-mail: {gaolon, fgaoaa}@zju.edu.cn initial values. Moreover, a multi-terminal fast path search algorithm is proposed to generate the initial values for opti- mization. Extensive simulation experiments demonstrate that our approach achieves several-fold improvements in efficiency compared to existing algorithms, while also ensuring lower curvature and trajectory duration. Real-world experiments involving the transportation, loading and unloading of goods in both indoor and outdoor scenarios further validate the effectiveness of our method. The source code is accessible at https://github.com/Tracailer/Tracailer. Note to Practitioners—This paper addresses the chal- lenges of motion planning for tractor-trailer robots, which are crucial in industries like logistics and agricul- ture. Our approach introduces a lightweight trajectory planning method that efficiently generates safe and time- optimal paths while considering the unique kinematic constraints of these vehicles. By utilizing the environ- ment’s collision-free areas, we enhance safety and reduce reliance on initial conditions. While our method shows significant efficiency improvements in simulations and real-world tests, its effectiveness may vary in extremely dynamic environments. Practitioners can easily adopt our open-source code to integrate this planning technique into their operations, improving the efficiency and safety of tractor-trailer systems and paving the way for future IEEE Transactions on Automation Science and Engineering (T-ASE) paper, presented at ICRA 2026, Vienna, Austria. Cite as T-ASE paper. ©2026 IEEE