Automatic control of a wheel loader doing bucket filling can be solved using deep reinforcement learning. This was recently demonstrated in a simulator environment by a team from Algoryx, Epiroc, and Umeå University. The scientific paper was recently published in the journal Machines. In underground mines, specialized wheel loaders (LHD) are used for loading fragmented […]
Soon, European factories will be designed and operated by artificial intelligence. The AIToC project develops Artificial Intelligence supported Tool Chains in Manufacturing Engineering to make this possible.
We used reinforcement learning to show that it’s possible to automate grasping of a randomly placed tree log with an AI-controlled forest machine.
Algoryx has used AGX Dynamics, Unity and ML-Agents for machine learning of an AI-controlled wheel loader.
AGX Dynamics for Unity has been verified by Unity Technologies to ensure it is optimized for the Unity real-time 3D development platform with a seamless user experience.
Algoryx participates in accelerator program TINC is arranged by Nordic Innovation House in Silicon Valley, USA
Algoryx is top ranked in the Swedish AI startup landscape, selected using criteria such as use of AI, scalability, access to and use of data, and the AI skills of their personnel.
Reports research conducted at Baidu Research where AGX Dynamics was used to set up a mechanical simulation of an excavator operating in terrain.
AGX Dynamics is well known for its fast and stable direct solver. In 2.19 we have improved the performance.