Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Improving ego localisation of a motorcycle to enable accurate AR anchor generation
AR headsets for motorcycles allow the rider to see all relevant information concerning
safety and infotainment without having to take his or her eyes off the road. For this to be a
pleasant experience virtual objects much be anchored precisely into the real world.
AR headsets for motorcycles allow the rider to see all relevant information concerning
safety and infotainment without having to take his or her eyes off the road. For this to be a
pleasant experience virtual objects much be anchored precisely into the real world. Which
can be a challenge on a highly dynamic motorcycle. Thus highly accurate ego localisation
of the vehicle is necessary to allow for stable AR anchors to be generated.
As part of a joint master thesis between the Computer Vision Lab and Aegis Rider AG an
ETH Pioneer Fellowship startup, you will improve the ego vehicle localisation using a
sensor fusion approach and combining: visual, inertial and GPS odometry for a highly
accurate vehicle pose estimation and tracking system.
**Requirements**: knowledge in robotics, sensor fusion, C++ and having worked with ROS1
or 2. Experience with AR is a nice plus.
AR headsets for motorcycles allow the rider to see all relevant information concerning safety and infotainment without having to take his or her eyes off the road. For this to be a pleasant experience virtual objects much be anchored precisely into the real world. Which can be a challenge on a highly dynamic motorcycle. Thus highly accurate ego localisation of the vehicle is necessary to allow for stable AR anchors to be generated. As part of a joint master thesis between the Computer Vision Lab and Aegis Rider AG an ETH Pioneer Fellowship startup, you will improve the ego vehicle localisation using a sensor fusion approach and combining: visual, inertial and GPS odometry for a highly accurate vehicle pose estimation and tracking system.
**Requirements**: knowledge in robotics, sensor fusion, C++ and having worked with ROS1 or 2. Experience with AR is a nice plus.