The task of transporting cars from the end of the assembly line to its final destination is currently a manual and expensive logistics problem. It includes loading and unloading of vehicles from the factory floor to trucks, ships and rail, with interim stops at parking lots. Seoul Robotics aims to change this. The company has just launched Level 5 Control Tower (LV5 CTRL TWR) system which BMW is leveraging to automate last-mile fleet logistics at their manufacturing facility in Munich.

The system uses SENSR™, a proprietary perception software powered by artificial intelligence (AI) algorithms. SENSR™ works in conjunction with a mesh network of computers and LiDAR sensors located on fixed infrastructure (light poles, roof overhangs, etc) that guides vehicles autonomously through a 5G communications network. Read More

Learning sensorimotor control policies from high dimensional images crucially relies on the quality of the underlying visual representations. Prior works show that structured latent space such as visual keypoints often outperforms unstructured representations for robotic control. However, most of these representations, whether structured or unstructured are learned in a 2D space even though the control tasks are usually performed in a 3D environment. In this work, we propose a framework to learn such a 3D geometric structure directly from images in an end-to-end unsupervised manner. The input images are embedded into latent 3D keypoints via a differentiable encoder which is trained to optimize both a multi-view consistency loss and downstream task objective. These discovered D keypoints tend to meaningfully capture robot joints as well as object movements in a consistent manner across both time and 3D space. The proposed approach outperforms prior state-of-art methods across a variety of reinforcement learning benchmarks. Read More

#image-recognition, #robotics