Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks
This work addresses the challenge of reducing human operator burden in industrial and automotive settings with partial automation, though it appears incremental as it builds on existing imitation learning techniques.
The paper tackles the problem of imitation learning for long-horizon tasks under partial automation by proposing the Disturbance Injection under Partial Automation (DIPA) framework, which robustly learns action and mode-switching policies and outperforms previous methods in simulations and a real robot environment, reducing the demonstration burden.
Partial Automation (PA) with intelligent support systems has been introduced in industrial machinery and advanced automobiles to reduce the burden of long hours of human operation. Under PA, operators perform manual operations (providing actions) and operations that switch to automatic/manual mode (mode-switching). Since PA reduces the total duration of manual operation, these two action and mode-switching operations can be replicated by imitation learning with high sample efficiency. To this end, this paper proposes Disturbance Injection under Partial Automation (DIPA) as a novel imitation learning framework. In DIPA, mode and actions (in the manual mode) are assumed to be observables in each state and are used to learn both action and mode-switching policies. The above learning is robustified by injecting disturbances into the operator's actions to optimize the disturbance's level for minimizing the covariate shift under PA. We experimentally validated the effectiveness of our method for long-horizon tasks in two simulations and a real robot environment and confirmed that our method outperformed the previous methods and reduced the demonstration burden.