Excavator Autonomous Driving

Jun 17, 2022

This project involves a wide range of technologies. My research and works on this has three directions, excavator arm motion planning, trajectory optimization, and control, crawler excavator base motion planning and control, and task-level planning involving decision-making.

To better support this project, besides my research and implementation, I have also developed a soil kinematic simulation based on ROS, and built a excavator robot system by modifying a mini-excavator, add sensors and make computer directly gives control commands, instead of using a joystick.

(The slides were written in Chinese.)

Reinforcement Learning Wheeled Robot Trajectory Optimization Robot Platform Simulation Environment

Publications

Excavation of fragmented rocks with multi-modal model-based reinforcement learning

This paper presents a multi-modal model-based reinforcement learning approach for excavating challenging fragmented rocks. It leverages a multi-modal recurrent neural network (RNN) and a model predictive controller (MPC) to outperform conventional strategies, demonstrating superior predictive accuracy and effectiveness in a challenging task.

Yifan Zhu, Liyang Wang, Liangjun Zhang

Excavation of fragmented rocks with multi-modal model-based reinforcement learning

Imitation Learning and Model Integrated Excavator Trajectory Planning

This paper presents a two-stage approach that integrates data-driven imitation learning and model-based trajectory optimization to enhance automated excavation techniques for excavators, resulting in a significant increase in excavation efficiency.

Qiangqiang Guo, Zhixian Ye, Liyang Wang, Liangjun Zhang

Imitation Learning and Model Integrated Excavator Trajectory Planning

Autonomous Wheel Loader Trajectory Tracking Control Using LPV-MPC

This paper outlines an approach for efficient trajectory tracking control of autonomous wheel loaders, employing nonlinear model predictive control for trajectory planning and a Linear Parameter Varying (LPV) model for enhanced computational efficiency, leading to better performance and reduced computational burden compared to conventional methods.

Ruitao Song, Zhixian Ye, Liyang Wang, Tianyi He, Liangjun Zhang

Autonomous Wheel Loader Trajectory Tracking Control Using LPV-MPC

Hierarchical planning for autonomous excavator on material loading tasks

This paper presents a hierarchical planning system for autonomous excavators, enhancing task and motion planning, and demonstrating its effectiveness in real-world and simulated excavation tasks.

Liyang Wang, Zhixian Ye, Liangjun Zhang

Hierarchical planning for autonomous excavator on material loading tasks

An autonomous excavator system for material loading tasks

This paper introduces an Autonomous Excavator System (AES) designed for material loading tasks in challenging environments. Combining advanced perception and planning algorithms, AES demonstrates autonomous operation with efficiency comparable to human operators and robust performance in complex scenarios, achieving 24-hour continuous operation without human intervention.

Liangjun Zhang, Jinxin Zhao, Pinxin Long, Liyang Wang, Lingfeng Qian, Feixiang Lu, Xibin Song, Dinesh Manocha

An autonomous excavator system for material loading tasks

Aes: Autonomous excavator system for real-world and hazardous environments

This paper emphasizes the potential of autonomous excavators to enhance safety and productivity by replacing human operators in hazardous conditions within a multi-billion-dollar global market.

Jinxin Zhao, Pinxin Long, Liyang Wang, Lingfeng Qian, Feixiang Lu, Xibin Song, Dinesh Manocha, Liangjun Zhang

Aes: Autonomous excavator system for real-world and hazardous environments