- Operation plan
Motion planning (picking, route generation)
Developed technologies for planning routes of self-driving cars or motion of robot arms.
- Reinforcement learning methods enable packing operations by robots with high filling rates.
- Graph search mehods generate safe and comfortable routes of self-driving cars.
- Expected to be applied in logistics robots and automatic driving.
Applications
- Picking robots on automated logistics lines
- On-board hardware/software for self-driving
Benchmarks, strengths, and track record
- Received the Outstanding Lecture Award at the 20th Society of Instrument and Control Engineers System Integration Division Symposium.
Inquiries
Please include the title “Toshiba AI Technology Catalog: Motion planning (picking, route generation)” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.
References:
- R. Katsuki et al. “Graph Search based Local Path Planning with Adaptive Node Sampling”, IEEE Intelligent Vehicles Symposium, 2018.
- Ryosuke Nonaka et.al.; “Driving lane selection in 100ms cycles using reinforcement learning”; 20th Society of Instrument and Control Engineers System Integration Division Symposium, 2019.
- T. Tanaka, et al., Simultaneous Planning for Item Picking and Placing by Deep Reinforcement Learning, IROS, 2020.
- Rie Katsuki et.al.; High-speed Lane trajectory generation using node sampling and taking into account obstacle avoidance patterns”; RSJ2020.