The latest software release has rolled out to the driverless fleet, containing improvements in these areas:
Improved core driving behavior
Shipped DLA v3 & KSE VRU v13 which improves tracking of bikes by up to 30%, allowing the AV to behave and respond more safely around these vehicles on higher speed roads
Shipped PSeg v5.1.5 that improves tracking by up to 25% for several classes of less common objects, such as animals and small debris in the road.
Shipped STA-V v24 that improves prediction of incoming cross traffic vehicles in the right lane when the AV is taking a right turn on major roads with splitting lanes by 15%
Shipped Vehicle MTL v3 which improves vehicle open door detections by 49%.
Shipped improvements to our ability to predict trajectories for articulated vehicles improving behavior around these vehicles by 20-30%.
Further increased safety on higher speed roads and low friction surfaces by giving the AV more lateral maneuverability to make evasive maneuvers when needed.
Shipped TREX V2 which improves the positioning of the AV when preparing to go around a double-parked vehicle and improves braking smoothness when traveling at higher speeds.
Improved AV performance and reliability when operating at very low speeds.
We improved the AV's ability to maintain lane positioning and speed at lane merges and forks when traveling at higher speeds.
Shipped TSEL v13 and v14 which improved maneuver completion around double parked vehicles on the road by 50%; including situations encountered during challenging high traffic day time environments.
Improved remote assistance reroute capabilities to support higher speed roads and better handle unexpected road closures.
Increased overall AV stability through bug fixes and improved fault tolerance.
Improved rider experience
Improved overall trip time in 12% of trips through improved routing and lane changes.
Added audio chime to remote door close scenario for better rider experience.
Improved feedback workflow post ride.
Statistics measuring the percentage of improvement are based on internal benchmarks and metrics.