1 Functions | 2 Reference Model | 3 I/O Data |
4 Functions of AI Modules | 5 I/O Data of AI Modules | 6 AIW, AIMs, and JSON |
7 AI Modules | 8 Data Types |
1 Functions
The functions of the Autonomous Motion Subsystem (AMS) are:
- Receive a request to reach a destination from the Human-CAV Interaction Subsystem (HCI).
- Request current Pose to Environment Sensing Subsystem (ESS).
- Converse with HCI and settle on final Route.
- Respond/request to specific Remote AMS requests.
- Produce Full Environment Representation.
- Generate Paths (Plath Planner).
- Generate Goal and Trajectory (Motion Planner).
- Check whether Trajectory can be implemented (Obstacle Avoider).
- Issue Command to Motion Actuation Subsystem.
- Process Message from Motion Actuation Subsystem (MAS).
- If required, AMS Command Issuer forwards information back to the chain’s AIM.
2 Reference Model
Figure 1 gives the Autonomous Motion Subsystem Reference Model.
Figure 1 – Autonomous Motion Subsystem Reference Model
The operation of the Autonomous Motion Subsystem unfolds as follows:
- A human requests the Human-CAV Interaction to take them to a destination.
- HCI interprets request and passes interpretation to the AMS.
- The AMS activates the Route Planner to generate a set of Waypoints starting from the current Pose (obtained from the ESS) up to the destination.
- The Waypoints enter the Path Planner which generates a set of Poses to reach the next Waypoint.
- For each Path, the Motion Planner generates a Trajectory to reach the next Pose.
- Obstacle Avoider receives the Trajectory and checks if an Alert was received.
- If an Alert was received, Obstacle Avoider detects whether the Trajectory created a collision.
- If a collision is detected, Obstacle Avoider requests a new Trajectory from Motion Planner.
- If no collision is detected, Obstacle Avoider issues an AMS-MAS Message to MAS.
- The MAS sends MAS-AMS Message about the execution of the Command.
- The AMS, based on the MAS-AMS Messages received conveying Environment information, may discontinue the execution of the earlier MS-MAS Message and issue a new AMS-MAS Message.
- The decision of each element of the said chain may be recorded in the Decision Recorder (“black box”).
3 I/O Data
Table 1 gives the input/output data of Autonomous Motion Subsystem.
Table 1 – I/O data of Autonomous Motion Subsystem
4 Functions of AI Modules
Table 2 gives the AI Modules of the Autonomous Motion Subsystem.
Table 2 – Functions of Autonomous Motion Subsystem’s AI Modules
AIM | Function |
Full Environment Description | Creates an internal representation of the Environment by fusing information from itself, Remote AMSs, and other CAV-aware entities. |
Route Selection Planner | Computes a set of possible Routes, through a road network, from the current to the target destination. |
Path Selection Planner | Generates a set of Paths, considering:
1. Route. |
Motion Selection Planner | Defines a Trajectory to reach a Goal using the Spatial Attitude:
1. Satisfying the CAV’s kinematic and dynamic constraints |
Traffic Obstacle Avoider | Checks whether Trajectory is compatible with Alert information:
If AMS Command Issuer informs Obstacle Avoider that AMS-MAS Message cannot be implemented, Traffic Obstacle Avoider may issue a “discontinue previous Command” and forward the Road State to the appropriate upstream AIM, possibly up to the Route Planner. This may decide to communicate the Road State to the Human-CAV Interaction Subsystem. |
AMS Command Issuer | Instructs the MAS to execute the Trajectory considering the Environment conditions and receives MAS-AMS Messages about the execution. Based on a Message, the Road State may be communicated to the Obstacle Avoider. |
AMS Decision Recorder | Records decisions by Route Planner, Path Planner, Motion Planner, Obstacle Avoider, and Command Issuer. |
5 I/O Data of AI Modules
Table 3 gives, for each AIM (1st column), the input data (2nd column) and the output data (3rd column) of Autonomous Motion Subsystem.
Table 3 – Autonomous Motion Subsystem’s data
AIM | Input | Output |
Full Environment Description | – Basic Environment Descriptors – Other data from Remote AMSs |
– Full Environment Descriptors |
Route Selection Planner | – Poses – Full Environment Descriptors – Offline Map Data – Road State – Selected Route |
– Route |
Path Selection Planner | – Route – Full Environment Descriptors – Offline Maps – Road State |
– Set of Paths |
Motion Selection Planner | – Set of Paths – Full Environment Descriptors – Road State |
– Trajectory |
Traffic Obstacle Avoider | – Trajectory – Full Environment Descriptors – Alert – Road State |
– Trajectory |
AMS Command Issuer | – Trajectory – MAS-AMS Message |
– AMS-MAS Message |
AMS Decision Recorder | – Route – Path – Trajectory – AMS-MAS Message – MAS-AMS Message |
– File of Recorded Data |
6 AIW, AIMs, and JSON Metadata
7 AI Modules
Initial versions of AIMs are available.
8 Data Types
Initial versions of Data Types are available.