The Drive to Level 5

Wrapping up our summer series on autonomous vehicles, our final Drive to Level 5  interview is with Willard Tu, Senior Director of Automotive Technologies at Xilinx. 

Willard will be giving his presentation on "Transportation as a Service" at The Drive World Conference in Santa Clara CA on Thursday August 29th.  The continuing evolution of autonomous vehicles has enormous implications for all of us. Whether it comes to fruition in five years or ten, this technology will change they way we work, they way we play and essentially how we live. 

But how this evolution takes place requires a number of different technologies to continue to develop and come together. Those include :

• Artificial Intelligence: Computer Vision vs. Neural Nets
  Computer Vision – demands more performance, which drives cost up and thermal dissipation, better suited for FuSa
  Neural Nets – are a true black box, but will likely be lower performance than Computer Vision and lower thermal
  
• Compute: Distributed vs. Centralized
  Most of the traditional passenger owned vehicles are driven by costs. These vehicles today are distributed intelligence so that OEMs can source an ECU = 1 function to a supplier. Centralization is much more complex as either the OEM or a Tier 1 has to take on greater responsibility for multiple functions that might be put into a centralized computing center.
  Centralization has trade-offs — you now have to stream a lot of data to a central node this is not easy. Cost is moved from processing at the edge to data transportation across the vehicle
  Robotaxi — vendors are doing it completely differently. They are all for centralization, cost as strong a consideration.
  
• Sensing: Camera, Radar, LiDAR
  We will discuss the trade-offs and likely cost projections of each technology.
  
• Processing Engines: CPU, DSP, FPGA, GPU
  Will contrast and compare each of these engines.
  Latency: Batch vs. Batch-less will be covered in this comparison.
  

In this interview Willard takes us through these technologies and discusses the implications autonomous vehicles have for all of us. 

LiDAR is the autonomous vehicle acronym that stands for Light, Detection and Ranging Technology.  How good is it now and how good will it get in the years to come? 

Zhenchun Xia is the Senior Engineer, ADAS Control Systems at Mitsubishi.  His presentation will address this topic at the Drive World Conference & Expo in Santa Clara CA on August 27th at 9:00 AM.  Zhenchun will be addressing how autonomous vehicles detect, range, and map the car's surroundings. Ideally, these cars will be operating in dry, sunny conditions. But what happens when it starts to rain, snow, or fog sets in? 

This session will take an in-depth look at how LiDAR works and if we can really rely on the technology in less than perfect driving conditions. Some testing results under adverse weather conditions will be discussed.

Zhenchun explains the capability and advantages/limits of LiDAR detections in the edge conditions, like very far distance (up to 200 - 300 meters), highly dense point cloud in specific environment (trees surrounding traffic interaction, etc), as well as the highly dynamic driving conditions (high speed of host vehicles and the targeting vehicles, etc).

The general LiDAR detections algorithm and the calibration technology will also be discussed.