# IL-ACT: Imitation Learning with Adaptive Cartesian Tracking Control for a 30-ton Excavator

arXiv: https://arxiv.org/abs/2609.16696 · HTML: https://mlsanity.com/paper/2609.16696/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 17 of 17)

- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation](https://mlsanity.com/paper/2405.05439/) (2024)
- [Stable-BC: Controlling Covariate Shift with Stable Behavior Cloning](https://mlsanity.com/paper/2408.06246/) (2024)
- [Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach](https://mlsanity.com/paper/2304.04066/) (2023)
- [MTIL: Encoding Full History with Mamba for Temporal Imitation Learning](https://mlsanity.com/paper/2505.12410/) (2025)
- [Optimization-Based Framework for Excavation Trajectory Generation](https://mlsanity.com/paper/2010.14038/) (2020)
- [Real-Time Motion Planning of a Hydraulic Excavator using Trajectory Optimization and Model Predictive Control](https://mlsanity.com/paper/2107.02366/) (2021)
- [Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery](https://mlsanity.com/paper/2412.07544/) (2024)
- [Efficient Model Learning and Adaptive Tracking Control of Magnetic Micro-Robots for Non-Contact Manipulation](https://mlsanity.com/paper/2403.14414/) (2024)
- [Robust Sensor-Limited Control with Safe Input-Output Constraints for Hydraulic In-Wheel Motor Drive Mobility Systems](https://mlsanity.com/paper/2409.11823/) (2024)
- [Anti-Slip AI-Driven Model-Free Control with Global Exponential Stability in Skid-Steering Robots](https://mlsanity.com/paper/2504.08831/) (2025)
- [Full- and Reduced-order Model of Hydraulic Cylinder for Motion Control](https://mlsanity.com/paper/1705.00916/) (2017)
- [Exponential Auto-Tuning Fault-Tolerant Control of N Degrees-of-Freedom Manipulators Subject to Torque Constraints](https://mlsanity.com/paper/2311.15852/) (2023)
- [Robust Model-Free Control Framework with Safety Constraints for a Fully Electric Linear Actuator System](https://mlsanity.com/paper/2409.12406/) (2024)
- [Physics-informed Neural Network Predictive Control for Quadruped Locomotion](https://mlsanity.com/paper/2503.06995/) (2025)
- [High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics](https://mlsanity.com/paper/2509.17387/) (2025)

## Abstract (arXiv)

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.