Autonomous Valet Parking hackathon and demonstration
The Autonomous Valet Parking functionality will provide the capability to automatically drive a car from a drop-off location (such as a carpark entrance) to a specified park, park the car, and then drive to a pick-up location upon request. This functionality will be performed at Level 4 autonomy, meaning a driver will not need to be present in the car.
The functionality is being developed according to five development milestones, each of which builds on the previous to provide increasingly complex autonomous valet parking capability.
The current target is Milestone #2. For details on the current status and progress, see that milestone's page.
- Milestone 1: Foundations
- Milestone 2: Follow waypoints with the NDT localizer
- Milestone 3: Integration of MS2 on the actual vehicle and replace trajectory record/replayer with a motion planner
- Milestone 4: Test on the vehicle with the real route planner and integrate HD map
- Milestone 5: Integration on the vehicle and physical parking lot
The AVP hackathon and demonstration is being managed by the Autonomy Software Working Group. Anyone who is commited to providing something for the demonstration, or anyone who is interested in participating, should join the ASWG's weekly meeting. For meeting times, see the Autoware Foundation's events calendar.
On December 10th, 2019, the Autoware Foundation conducted a one-day workshop led by the Autonomy Software Working Group and hosted by Apex.AI in Palo Alto, California.
The goals of this workshop were:
Plan in detail the development activities and monthly milestones for a successful AVP hackathon and demo in April 2020 (see below)
Design the system architecture to the point of node allocations
The outcome of the planning workshop can be seen on this page. Amongst other things, the five milestones listed above and a first-pass architecture were produced.
On the same day, Apex.AI hosted an evening Autoware meetup.
Demonstration and hackathon
The Autoware Foundation plans to demonstrate the AVP functionality on the 24th of April, 2020 in Palo Alto, California. In the week leading up to this demonstration, a hackathon will be held in Palo Alto from April 20th to April 23rd, to polish off the demo and handle any final tasks.
The goal of the hackathon is to polish off the Autonomous Valet Parking use case functionality and finalise getting it working on a real vehicle.
Because it is not feasible to be implementing self-driving functionality within four days, the intention is to have the necessary functionality in Autoware.Auto completed before the hackathon starts. A simulation of the demonstration location in the LGSVL simulator will be used for testing and development by most developers prior to the hackathon.
Schedule and location
The hackathon will take place over five days in the week of April 20th, 2020. The first four days will be dedicated to finalising the demonstration and fixing any remaining issues in Autoware.Auto. The final day will be the demonstration itself.
The hackathon will be held at Apex.AI's office in Palo Alto, California. The demonstration itself being held at the AutonomouStuff parking lot, which is about ten minutes' (manual) drive away.
- The Velodyne driver will be the one developed originally for Autoware.Auto by Apex.AI and being pushed to the
ros-driversrepository for ROS 2.
- Localisation will be performed using the deterministic NDT implementation now integrated into Autoware.Auto.
- Obstacle detection will be based on the euclidean clustering implementation present in Autoware.Auto.
- Planning will use an open-source planner provided by Embotech.
- Motion control will use a deterministic implementation of MPC currently being integrated into Autoware.Auto.
- The vehicle interface will be provided by AutonomouStuff, who have just recently completed a ROS 2 version of their PACMod driver and considering a port of their Speed and Steering Control software stack.
- The map format used will be OpenDrive.
- Safety will be achieved via an emergency stop, due to the low speed.
The hackathon and demonstration will be performed using Apex.AI's Lexus. This SUV has two Velodyne 16s mounted front and back for localisation and obstacle detection, an advanced GPS/IMU sensor, and a Nuvo computer.
Discussion of the AVP hackathon and demonstration
Discussion about the above plans is held at the ROS Discourse and in GitLab issues on the Autoware.Auto projects. Initial discussion is in this thread. Technical discussion should be held in the GitLab issues for the Autoware.Auto projects while more casual discussion should be held in the Autoware category of the ROS discourse.