Autonomous vehicles move fully or partly without human intervention, using cameras, radar, lidar and AI software. The SAE J3016 standard defines six levels – from 0 (no automation) to 5 (fully driverless everywhere). AI handles perception, predicting the behaviour of other road users and route planning. Besides cars, this covers robotaxis, lorries, shuttles and warehouse vehicles; approval and liability are regulated separately in each country.
AI in transport covers applications in logistics, traffic and mobility: route and tour planning, traffic forecasting, predictive maintenance of vehicles and infrastructure, and driver assistance systems through to autonomous vehicles. The aims are shorter routes, fewer empty runs, lower costs and greater safety. Many applications are safety-critical and therefore strictly regulated. Example: a parcel service re-plans its delivery rounds every day based on shipment volume and traffic conditions.
Computer vision is a field of AI in which computers interpret images and video. Typical tasks include detecting and locating objects, reading text in images and measuring components. The technology is used, for example, in quality control in manufacturing, in driver assistance systems, in logistics and in medical imaging.
Depth estimation determines from images how far objects or individual pixels are from the camera. This can be done with two cameras (stereo), with depth sensors or, using neural networks, even from a single photo (monocular depth estimation). It is needed in robotics, driver assistance, augmented reality and 3D models of rooms.
Reinforcement learning is a branch of machine learning in which an agent learns by trial and error. It acts within an environment, receives rewards for good outcomes and penalties for bad ones, and in this way develops a strategy that maximises its overall reward. Well-known examples include programs that master board games such as Go, robot control and the fine-tuning of language models based on human ratings.
