Autonomous Driving and HD Maps
Co-Founder & CTO
Why Autonomous Driving?
• Fewer accidents
• Road crashes lead to 3000 deaths and 100,000 injured worldwide a day.
• Decreased traffic congestion
• Enhanced human productivity
• Reduced cost of ride sharing
• Fewer parking lots, and no more parking headaches
• Improved mobility for the people who cannot drive
History of Autonomous Driving1986
CMU Navlab 12005
Stanford Stanley1st in DARPA Grand Challenge
1st in DARPA Urban Challenge
Different Levels of Autonomy
Two Different Approaches
Level 4 Players in the US
Comparison of Level 4 Players in the US
Level 4 Players in ChinaBaidu
Commercialization in 3 years,mass production in 5 years.
UiSeeUrban Mobile Box
iDriver+Autonomous Street Sweeper
How do Autonomous Cars Work?
Sensors on an Autonomous Car
• Dynamic objects• Detection
• Traffic sign & light recognition
Localization: Differential GNSS
Localization: LiDAR Reflectivity Map Matching
LiDAR reflectivity map Correlation of real-time scan and map
Mission & Path Planning
• Traffic rules / logics
• Obstacle avoidance
• Safety metrics
• Vehicle dynamics
• Vehicle dynamic models
• Control algorithms• Traditional PID control
• Dynamic perfect control
• Neural network control
High-Definition (HD) Maps
• Road network layer• Traffic sign, lights, poles
• Lane markers
• Perception layer• Static features
• Localization layer• Reflectivity
HD Map Generation Pipeline
Road network layer
Efficient 3D Representation Using Octree
Road Network Representation
Challenges and Potential Improvements
• Construction zones:• Additional radio signals to guide traffic, and
• Construction plans filed in advance and available to autonomous cars.
• Traffic lights:• Radio signals to indicate state, or at least
• Clear visibility to car’s cameras, regardless of the sun’s position.
• School bus, ambulance, and other emergency service vehicles:• Additional radio signals to indicate state.