Excavator control improved with adaptive imitation learning method
IL-ACT: Imitation Learning with Adaptive Cartesian Tracking Control for a 30-ton Excavator
Robotics
Summary
Controlling large excavation machines is hard because their parts move together, respond slowly, and have unpredictable behavior. The researchers designed a new method that learns from expert operators and adjusts commands in real time to better track desired movements. They tested their method in detailed simulations and found it completes tasks faster and more accurately than previous approaches. This could help excavators work more autonomously and efficiently in the future.
What this means in practice
- •For construction equipment engineers: Implement adaptive learning-based control for autonomous excavation to improve task precision and efficiency under unpredictable conditions.
- •For robotics system integrators: Develop control frameworks for heavy machinery that combine imitation learning with adaptive feedback to handle complex kinematics and delays.
Authors
Mehdi Heydari Shahna, Seihun Kim, Soyi Jung, Soohyun Park, Jouni Mattila, Joongheon Kim
Abstract
Autonomous excavator control is challenged by coupled kinematics, actuation lag, and uncertainty. We propose imitation learning and adaptive Cartesian tracking (IL-ACT), a novel motion control framework for a 30-ton-class excavator. An anchored, 14-input imitation policy pretrained on operator demonstrations generates nominal joint rates; adaptive Cartesian feedback and gated gain/bias estimation correct these commands before a stopping-distance governor constrains joint-reference generation. Simscape evaluation covers 100 sequential goals and spiral, figure-eight, and rounded-raster tracking, including 88 additional runs across three training seeds, two initializations, and speeds, under hydraulic response and sensing conditions. Compared with Teacher+ACT, IL-ACT completes all goals with shorter duration and lower terminal errors under both response conditions. Telemetry-initialized IL-ACT lowers RMSE in all 24 figure-eight and rounded-raster seed comparisons and lowers additional-load spiral mean RMSE by approximately 29%. Original spiral RMSE also improves over IL-only and PID. Under a shared sensor-noise realization, telemetry-initialized IL-ACT achieves 27.67% lower mean RMSE than Teacher+ACT; enabling estimation reduces mean RMSE by $22.44\%$ relative to the frozen estimator. Pretrained-weight effects remain mixed, and the original teacher comparison exhibits a spiral RMSE--maximum-error tradeoff. Analysis establishes bounded adaptive states and Cartesian feedback, with reference admissibility conditional on governor feasibility.