It is so great to see that our research partner, NTU professor Lyu Chen’s group has made significant progress on their autonomous research in the past one year since the delivery of our Ackermann-driven mobile autonomous robot in July 2020, refer to the news here for the robot delivery: Weston Robot Delivered Ackerman-Driven Autonomous Robot to NTU

Reported by NTU recently, Prof. Lyu’s group (AutoMan)) took home two awards at an autonomous driving competition organised by Waymo, the autonomous-vehicle subsidiary of Google. Using algorithms they developed, the team was able to predict where a vehicle would be eight seconds in the future with high accuracy – about 30 cm away from the actual position in real-world data. The team was the sole winner in the Interaction Prediction category, and also clinched 2nd place in the Motion Prediction category.

There were 70+ international teams from academia and industry competing to develop software algorithms that could analyse 574 hours of real-world traffic data from Waymo, which consisted of vehicles, pedestrians and cyclists, as well as infrastructure such as traffic lights. Using a combination of deep learning and custom algorithms, the software accurately predicted the motion of traffic and road users such as cyclists and pedestrians, which is extremely challenging in autonomous driving due to the complexity of the real-world environment, according to NTU.

Asst Prof Lyu said their traffic prediction technologies "have been proven in both simulations and in self-driving robots and will now be looking to integrate and test them on the full-sized autonomous electric bus. The self-driving robot is engineered by Weston Robot’s team based on its flagship robot HUNTER. The robot is proven to be cost effective, and yet and support seamless algorithms migration to full-sized autonomous electric bus.

Again, kudos to our research partners at NTU, looking forward to seeing exciting research in future: