OBJECT PATH PREDICTION METHOD, APPARATUS, AND PROGRAM, AND AUTOMATIC OPERATION SYSTEM

• US 20140303883A1
• Filed: 06/23/2014
• Published: 10/09/2014
• Est. Priority Date: 02/28/2006
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: KINDO, Toshiki, ASO, Kazuaki
• Granted Patent: US 10,102,750 B2
• Time in Patent Office: Days
• US Class Current: 701/300
• CPC Class Codes: B60W 2554/4041 Position
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 30/08 Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: B60W 30/10 Path keeping cruise control for automatically following a preceding vehicle B60W30/165
• CPC Class Codes: B60W 30/16 Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
• CPC Class Codes: B60W 40/02 related to ambient conditions
• CPC Class Codes: G08G 1/161 Decentralised systems, e.g. inter-vehicle communication
• CPC Class Codes: G08G 1/164 Centralised systems, e.g. external to vehicles
• CPC Class Codes: G08G 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

An object path prediction method, apparatus, and program and an automatic operation system that can secure safety even in situations that can actually occur are provided. For this purpose, a computer having a storage unit that stores the position of an object and the internal state including the speed of the object reads the position and internal state of the object from the storage unit, generates trajectories in a space-time consisting of time and space from changes of the positions that can be taken by the object with the passage of time based on the read position and internal state of the object, and predicts probabilistically paths of the object by using the generated trajectories.

Claims

1. An object path prediction method for predicting paths of a plurality of objects by a computer having a storage unit that stores at least positions of the plurality of objects and an internal state including a speed of each object, comprising:

a trajectory generation step of generating a trajectory in a space-time constituted by time and space from changes of the position that can be taken by each of the plurality of objects with a passage of time based on, after reading the positions and the internal states of the plurality of objects from the storage unit, the read positions and the internal states of the objects;

a prediction step of probabilistically predicting the paths of the plurality of objects by using the trajectories generated in the trajectory generation step; and

an interference level calculation step of calculating, based on results of prediction in the prediction step, a level of interference quantitatively showing an extent of interference between the paths that can be taken by a specific object and those that can be taken by other objects.

2. The object path prediction method according to claim 1, wherein the interference level calculation step

increases or decreases a value of the level of interference between the specific object and each of the other objects by a specified quantity in accordance with a number of times that the specific object and each of the other objects move closer than an interference distance, which is a spatial distance at which objects interfere with each other.

3. The object path prediction method according to claim 2, wherein the interference level calculation step

increases, when the specific object and one of the other objects move closer than the interference distance, the value of the level of interference between both objects moving closer in proportion to a collision probability of the both objects in the space-time.

4. The object path prediction method according to claim 2, wherein the interference level calculation step

increases, when the specific object and one of the other objects move closer than the interference distance, the value of the level of interference between both objects moving closer in proportion to a magnitude of a relative velocity at a time when the both objects move closer.

5. The object path prediction method according to claim 2, wherein the storage unit stores a magnitude of a relative velocity during collision between different objects by associating with a damage scale evaluation value for evaluating a scale of damage caused by the collision or an amount of damage losses caused by the collision and

the interference level calculation step reads, when the specific object and one of the other objects move closer than the interference distance, the damage scale evaluation value or the amount of damage losses in accordance with the magnitude of the relative velocity at a time when both objects move closer from the storage unit and increases the level of interference between the both objects in proportion to the damage scale evaluation value or the amount of damage losses.

6. The object path prediction method according to claim 1, wherein the trajectory generation step includes

an operation selection step of selecting an operation performed on the object from a plurality of operations,

an object operation step of causing the operation selected in the operation selection step to be performed for a predetermined period of time, and

a determination step of determining whether or not the position and the internal state of the object after the operation selected is performed in the object operation step satisfy control conditions concerning control of the object and movement conditions concerning movable areas of the object, wherein

a set of processing from the operation selection step to the determination step is repeatedly performed until a trajectory generation time in which the trajectory is generated has reached.

7. The object path prediction method according to claim 1, further comprising

a path selection step of selecting a path to be taken by the specific object contained in the plurality of objects in accordance with the level of interference calculated in the interference level calculation step.

8. The object path prediction method according to claim 7, wherein the level of interference has a larger value as an extent of interference between paths that can be taken by the specific object and those that can be taken by the other objects decreases and

the path selection step selects a path whose level of interference is maximal.

9. The object path prediction method according to claim 7, wherein the trajectory generation step includes

an operation selection step of selecting an operation performed on the object from a plurality of operations,

an object operation step of causing the operation selected in the operation selection step to be performed for a predetermined period of time, and

a determination step of determining whether or not the position and the internal state of the object after the operation selected is performed in the object operation step satisfy control conditions concerning control of the object and movement conditions concerning movable areas of the object, wherein

a set of processing from the operation selection step to the determination step is repeatedly performed until a trajectory generation time in which the trajectory is generated has reached.

12. A computer-readable recording medium that stores therein a computer program for performing an object path prediction, the computer program causing a computer to execute the object path prediction method according to claim 1.

10. An object path prediction apparatus, comprising:

a storage unit that stores at least positions of a plurality of objects and an internal state including a speed of each object;

a trajectory generation unit that generates a trajectory in a space-time constituted by time and space from changes of the position that can be taken by each of the plurality of objects with a passage of time based on, after reading the positions and the internal states of the plurality of objects from the storage unit, the read positions and the internal states of the objects;

a prediction unit that probabilistically predicts the paths of the plurality of objects by using the trajectories generated by the trajectory generation unit; and

an interference level calculation unit that calculates, based on results of prediction by the prediction unit, a level of interference quantitatively showing an extent of interference between the paths that can be taken by a specific object and those that can be taken by other objects.

11. The object path prediction apparatus according to claim 10, further comprising

a path selection unit that selects a path to be taken by the specific object in accordance with the level of interference calculated by the interference level calculation unit.