Autonomous Ground Systems Systems Architecture for Semantic Information-Sharing in Unmanned Convoys Dr. Jeffrey L. Ferrin Taylor C. Bybee Autonomous Solutions, Inc. 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited.
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2X) are common abstractions of sharing information. • Sensors like cameras and LiDAR have too much information to share over network. • Even if a network could handle that volume, the needed processing power on the receiving end would be astronomical! • Solution? – Achieve data compression by using mathematical models. – Rather than raw sensor data, share some semantic mathematic abstraction. 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 2
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Messaging occurs in broadcasts. • Anyone in the network can send and receive data. • Information-sharing can be designed as request-response messaging in pub-sub architecture. 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 3
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 4
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Terrain can be represented in a variety of ways. • We choose to use a heightmap. • We use tiled maps to represent the areas. • Heightmap cells have information such as – Elevation estimate – Elevation estimate variance – Slope – Valid/Predicted/Invalid 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 5
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 6
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys Tiles are used to represent heightmap and occupancy grid. 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 7
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Fusing heightmap and occupancy grid tiles – Assume independent cells for a simple model – Use weights based on variance estimates, source of new information, timing of information, etc. 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 8
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Publish-Subscribe (ROS) Implementation Thread Callback(s) Purpose 1 Main Process point cloud – Request-response function data for terrain estimation. communication needs to be in 2 Periodic Broadcast a terrain Callback request, wait, and a separate thread so other process responses callbacks remain from the received queue. uninterrupted. 3 Terrain Receives responses, Response inserts these – Utilizes callback queues in Callback responses into the receiving queue. each thread. 4 Terrain Receives request – Mutexes are used to ensure Request messages, publishes a Callback response with any thread-safety. available data. 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 9
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Gazebo Simulator – Two simulated Ford Escapes – Terrain with trees – Three trees of interest as obstacles 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 10
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • With terrain-sharing, the terrain-obstacle segmentation algorithm should • Have increased awareness of obstacles (from a farther distance) • Have increased awareness of terrain (from a farther distance) • Reduce false positives of obstacles 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 11
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • • Analysis Parameters – Post-processed both terrain- – Terrain is requested by each sharing and no terrain-sharing vehicle every 10 seconds. scenarios. – Examined the number of allocated heightmap cells near each obstacle. – Examined the number of LiDAR points classified as non- terrain (obstacle) on each obstacle. 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 12
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Obstacle #1 (First Tree) – Significantly more LiDAR points are segmented as an obstacle farther away with the terrain-sharing. – More heightmap cells are allocated at a farther distance with terrain-sharing. Red – Without Terrain Sharing Green – With Terrain Sharing 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 13
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Obstacles #2 and #3 – Significantly more LiDAR points are segmented as an obstacle farther away with the terrain-sharing. – More heightmap cells are allocated at a farther distance with terrain-sharing. Red – Without Terrain Sharing Green – With Terrain Sharing 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 14
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Obstacle #1 (First Tree) – Significantly more LiDAR points segmented as obstacle farther away with the terrain- sharing. – More heightmap cells are allocated at a farther distance with terrain-sharing. Red – Without Terrain Sharing Green – With Terrain Sharing 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 15
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • • Vehicles Experiment Parameters – Post-processed both terrain- – Terrain is requested by each sharing and no terrain-sharing vehicle every 10 seconds. scenarios. – Two Ford Escapes – Examined the number of – VLP16 LiDAR allocated heightmap cells near – Ubiquiti Bullet Radios each obstacle. – Examined the number of LiDAR points classified as non- terrain (obstacle) on each obstacle. 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 16
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • • Ford Escapes Road and obstacle 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 17
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Obstacle #1 (First Tree) – Approximately the same number of segmented LiDAR points for both cases. – Increased number of observed heightmap cells farther away. – Fewer false positives in adjacent area segmentation with terrain-sharing Red – Without Terrain Sharing Green – With Terrain Sharing 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 18
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • Obstacle #1 (First Tree) – Approximately the same number of segmented LiDAR No sharing points for both cases. – Increased number of observed heightmap cells farther away. – Fewer false positives in adjacent area segmentation with terrain-sharing Sharing 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 19
Autonomous Ground Systems Architecture for Semantic Information- Systems Sharing in Unmanned Convoys • • Conclusions Future Work – Preliminary results are – Sharing other types of geo- promising spatial information. – Need to be careful about how – Quantify how terrain-sharing conflicting information is can improve path control, handled. (Race conditions.) lateral stability, and safety. – Has been demonstrated at ASI for a manned explorer mapping obstacles with LiDAR, and passing to a follower with no sensors. 8/9/2018 UNCLASSIFIED: Distribution Statement A. Approved for public release; distribution is unlimited. 20
Recommend
More recommend
