More information
More information can be found at digitalphysics.se and xscave.eu.
Research project Heavy mobile machinery are designed to physically manipulate their surroundings. In XSCAVE, we combine computational physics with artificial intelligence (AI) to create safe and efficient systems for autonomous control.
Heavy mobile machinery are designed to physically manipulate their surroundings. They must be safe and reliable but adapt quickly to sudden changes in the environment. Balancing these seemingly contradictory requirements is the goal XSCAVE, acronym for “Explainable, Safe, Contact-Aware Planning and Control for Heavy Machinery Manipulation and Navigation.” Computational physics and artificial intelligence is combined to create safe and efficient autonomous control. The results are demonstrated on forest machines, earthmoving equipment, and outdoor logistics robots.
Earthmoving, forestry, and urban logistics are sectors where increased autonomy can spur drastic economic growth along with addressing labor shortage and negative environmental impact. Yet there are persisting challenges related to variations of tasks/environments that are intricately linked to the terrain machine contact encountered during navigation and manipulation. For example, an excavator needs to adapt to different types of soil conditions and rocks of different shapes and sizes. Such task and environment adaptation require machines to modify their “perception-to-action” mapping based on online observations from different sensing modalities.
XSCAVE will leverage the exceptional representation and approximation capabilities of deep neural networks to automatically learn the terrain/specific adaptation of excavation, forwarding, and navigation strategies from data. The overall objective of XSCAVE is: (i) to develop capabilities for learning performant (high-speed), safe (stable, contact-aware), and explainable perception-to-action models for terrain adaptive excavation and navigation strategies; and (ii) demonstrate step-change in autonomy in the construction, forestry and logistics industries.
To this end, XSCAVE aims to re-imagine deep-learned models as neural networks augmented with parameterized structured priors derived from physics, optimization, and classical search to bring domain knowledge into the learning pipeline. The fundamental innovations at the algorithmic level will translate to unprecedented ability for the machines to plan, control and adapt their actions depending on the task and terrain contact conditions.
The project is funded by EU-Horizon and run in collaboration between Aalto University, Algoryx, Forschungszentrum Informatik, Clevon, Czech Technical University in Prague, Komatsu Forest, Novatron, Tampere University, Toshiba Europe, Umeå University, University of Tartu.
More information can be found at digitalphysics.se and xscave.eu.