Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
175 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A path planning and path-following control framework for a general 2-trailer with a car-like tractor (1904.01651v2)

Published 2 Apr 2019 in cs.RO

Abstract: Maneuvering a general 2-trailer with a car-like tractor in backward motion is a task that requires significant skill to master and is unarguably one of the most complicated tasks a truck driver has to perform. This paper presents a path planning and path-following control solution that can be used to automatically plan and execute difficult parking and obstacle avoidance maneuvers by combining backward and forward motion. A lattice-based path planning framework is developed in order to generate kinematically feasible and collision-free paths and a path-following controller is designed to stabilize the lateral and angular path-following error states during path execution. To estimate the vehicle state needed for control, a nonlinear observer is developed which only utilizes information from sensors that are mounted on the car-like tractor, making the system independent of additional trailer sensors. The proposed path planning and path-following control framework is implemented on a full-scale test vehicle and results from simulations and real-world experiments are presented.

Citations (68)

Summary

  • The paper presents a lattice-based path planning system that generates collision-free paths for complex 2-trailer maneuvers including both forward and backward motion.
  • The paper develops a robust path-following controller that stabilizes lateral and angular errors using a nonlinear observer reliant solely on tractor sensors.
  • The paper demonstrates real-world implementation on a full-scale test vehicle, highlighting its potential for automated operations in commercial settings.

Path Planning and Control Framework for Complex Vehicle Systems

This paper presents a sophisticated path planning and path-following control framework tailored explicitly for maneuvering a general 2-trailer (G2T) with a car-like tractor. The difficulty of controlling such vehicles, especially in backward motion, is emphasized, noting the high skill level required and the potential automation advantages the proposed system could bring to various commercial domains like mines, harbors, and airports.

Technical Contributions

Path Planning and Path-following Control

The framework employs a lattice-based path planning methodology to generate collision-free paths for the G2T system, integrating backward and forward movements to handle complex maneuvers such as parking and obstacle avoidance. The lattice planner utilizes a precomputed library of motion primitives—each computing feasible paths between discrete states in a regularly discretized state-space. These primitives are derived from optimal control problem solutions that respect the vehicle's kinematic constraints.

Furthermore, a path-following controller stabilizes the lateral and angular errors during path execution, facilitated by state information estimated through a nonlinear observer. This observer is notable for its independence from additional sensors on trailers, relying solely on data from the tractor's sensors.

Real-world Implementation

The framework has been implemented on a full-scale test vehicle, evidencing practical application through simulations and real-world tests. The results showcase the system's capability to automatically execute advanced maneuvers, reinforcing its utility in commercial settings.

Implications and Future Directions

The presented framework not only holds practical implications by alleviating operational burdens in industries employing complex trailer systems but also introduces a strong theoretical foundation for motion planning and control in nonholonomic systems. With the introduction of real-time capable lattice-based planning, this system could significantly reduce planning times while maintaining path optimality.

Future developments may center on enhancing the planner's heuristic capabilities to better handle the curse of dimensionality, potentially integrating machine learning techniques. Moreover, incorporating dynamic obstacle handling within the planner could increase its versatility and applicability across more dynamic environments.

Conclusion

In summary, this research contributes a complete system design for autonomous path planning and execution on complex vehicle systems. The scalability and efficiency of the approach position it well for broad applications across several industries looking to leverage autonomous vehicle technologies. The extensive groundwork of this paper sets a solid premise for continued exploration and advancement in autonomous vehicle path planning and control systems.

Youtube Logo Streamline Icon: https://streamlinehq.com