Autonomous Robotic Arm Manipulation for Planetary Missions using Causal Machine Learning
This addresses the challenge of time-efficient and productive planetary exploration missions for space agencies, though it appears incremental as it builds on existing causal and reinforcement learning techniques.
The paper tackles the problem of enabling autonomous robotic arms to study unknown objects like planetary rocks without prior knowledge or training data, using causal machine learning in a simulated environment, and demonstrates that the method works effectively under realistic planetary conditions.
Autonomous robotic arm manipulators have the potential to make planetary exploration and in-situ resource utilization missions more time efficient and productive, as the manipulator can handle the objects itself and perform goal-specific actions. We train a manipulator to autonomously study objects of which it has no prior knowledge, such as planetary rocks. This is achieved using causal machine learning in a simulated planetary environment. Here, the manipulator interacts with objects, and classifies them based on differing causal factors. These are parameters, such as mass or friction coefficient, that causally determine the outcomes of its interactions. Through reinforcement learning, the manipulator learns to interact in ways that reveal the underlying causal factors. We show that this method works even without any prior knowledge of the objects, or any previously-collected training data. We carry out the training in planetary exploration conditions, with realistic manipulator models.