Outrider, a leader in autonomous freight yard operations, has announced the deployment of advanced reinforcement learning (RL) techniques to enhance its system’s efficiency and safety. By utilizing AI and RL models, Outrider has been able to increase path planning speed by 10x, allowing for smoother and faster movement of freight through busy distribution yards.
Vittorio Ziparo, CTO and executive vice president of engineering at Outrider, explained that through training and evaluating their system with RL in simulation and real-world scenarios, customers have seen significant improvements in speed and efficiency. Outrider’s AI-driven capabilities are further supported by redundant safety mechanisms, combining the benefits of AI with traditional safety approaches to ensure industrial operations are conducted securely.
By leveraging years of data samples and developing an RL curriculum of increasing difficulty, Outrider’s system is able to reinforce preferred behaviors such as following traffic rules and maintaining safe distances from other vehicles. Once extensively tested in simulation and on-vehicle at their Advanced Testing Facility, the RL models are deployed into autonomous operations at customer sites.
Outrider’s commitment to safety is evidenced by addressing over 200,000 safety scenarios and receiving validation from third-party safety experts and Fortune 500 customers. With the integration of advanced RL techniques, Outrider continues to push the boundaries of autonomous freight yard operations while ensuring the highest standards of efficiency and safety for its customers.
Source
Photo credit www.sdcexec.com