Toyota Claims its ML Ends Need of Real-World Autonomous Testing

Toyota is claiming its machine learning algorithms can make real-world testing of autonomous driving technology redundant.

Its US technology wing, the Toyota Research Institute (TRI), has presented six research papers in the field of machine learning at the International Conference on Computer Vision (ICCV). It claims the research advances understanding across various tasks crucial for robotic perception, including semantic segmentation, 3D object detection and multi-object tracking.

Its researchers have been working for six years on the technology at its three sites in Los Altos, California; Cambridge, Massachusetts, and Ann Arbor, Michigan. It says advances in robotics, automated driving and materials science are owing, in large part, to the application of computer algorithms that constantly improve with experience and data.

In the six papers accepted at ICCV, TRI researchers report several key findings claiming they show that geometric self-supervised learning significantly improves sim-to-real transfer for scene understanding. The resulting unsupervised domain adaptation algorithm enables recognizing real-world categories without requiring any expensive manual real-world labels.

In addition, its research on multi-object tracking suggest that synthetic data could endow machines with fundamental human cognitive abilities, like object permanence, that are historically hard for machine learning models but second nature for humans. This new development increases the robustness of computer vision algorithms, making them more aligned with people’s visual common sense.

Finally, the research on pseudo-LiDAR shows that large-scale self-supervised pre-training considerably boosts performance of image-based 3D object detectors. The proposed geometric pre-training enables training powerful 3D Deep Learning models from limited 3D labels, which are expensive or sometimes impossible to get from images alone.

Dr Gill Pratt, CEO of TRI, said: “Machine learning is the foundation of our research. We are working to create scientific breakthroughs in the discipline of machine learning itself and then apply those breakthroughs to accelerate discoveries in robotics, automated driving, and battery testing and development.”

— Paul Myles is a seasoned automotive journalist based in Europe. Follow him on Twitter @Paulmyles_

Leave a comment

Your email address will not be published. Required fields are marked *