Autonomous vehicle test at a limited field or even on the public road has its limitations. Simulation is essential to increase the test coverage. Taiwan Semiconductor Research Institute(TSRI) develop an autonomous vehicle test system based on CarMaker, which is a simulation tool from IPG Automotive. 13 testing scenarios and 6 testing routes corresponding to the physical test at Shalun testing field are built and included in this autonomous vehicle test system. An AEB(Autonomous Emergency Braking) function will be demonstrated to show how this autonomous vehicle test system works.

In this study, the embedded LiDARAI recognition of smart headlight for autonomous driving is demonstrated. At driving process, the vehicle can provide artificial intelligence to identify the type, distancespeed of the object to be measured based on the fusion data of the LiDAR point cloudoptical image of the environment,then feedback to the headlight control system. Finally, this smart headlight would perform the suitable lighting mode during the daynightfit the automotive lamp safety regulationsstandards (ECE R112SAE J3069).

In autonomous driving, LiDAR can clearly distinguish the objectsget the object information such as speeddistance at medium-range (~100 m) for autonomous driving scheme entering Level 3. Therefore, in this study, we combine the reflective optical phased array (OPA) chip1550-nm VCSELs with a photodetector, a ToF chip,a microcontroller to produce an eye-safe, all-solid-state,low cost (less than $100 USD) LiDAR module, which is the world＇s leading LiDAR technologymore cost-effective than the current products for autonomous vehicle market.

Low-power deep learning accelerator integrates neural network design / training, model compressionaccelerator design. It uses a small amount of computationmemory footprint to realize high performance on the edge device. The image semantic segmentation technology can reach 80 frames per second (resolution:1024*2048) to meet real-time requirements for autonomous driving.

Drone delivery is a popularemerging application at present. However, existing drone delivery systems can only deliver to outdoor open spaces via GPS,cannot directly to the interior of recipient＇s building. In the era of covid-19 pandemic, we aim to reduce human contactpropose a drone delivery system that can deliver packages to the doorstepthe interior of buildings,to achieve fully automatic control of the drone by developing visual positioning technique.