Space-Time Trajectory Prediction for Dynamic Obstacle Avoidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current automatic operation technologies for movable bodies, such as automobiles, struggle to predict safe paths when the range of movement is wide, as they cannot account for dynamic obstacles and require impractically long calculation times to avoid collisions.

Innovation Solution

An object path prediction method that generates trajectories in space-time based on an object's position and internal state, using a probabilistic approach to select operations and determine control conditions, allowing for real-time path prediction and interference level calculation to ensure safety.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If path finding technology is used to calculate paths in advance, then collision avoidance can be achieved, but calculation time becomes impractically long for wide-range movements

Engineering Contradiction:
Improvecollision avoidanceVSAvoidcalculation time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent divides the calculation process into two segments: (1) pre-calculation of static path components and (2) real-time calculation of dynamic obstacle avoidance. By segmenting the computation based on time requirements, the system achieves both thorough collision avoidance and practical response times.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary calculation of paths avoiding static obstacles before the movable body actually moves. This pre-computation of static path components allows the system to focus real-time computational resources only on dynamic obstacle detection and avoidance, significantly reducing overall calculation time.

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If the range of movement is wide, then mobility is improved, but the influence of dynamic obstacles spreads out making path calculation impossible in advance

Engineering Contradiction:
Improverange of movementVSAvoidpath calculation accuracy
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent transitions from static path planning to dynamic path adjustment. The system continuously updates the path based on real-time detection of dynamic obstacles, allowing the movable body to adapt to changing conditions while maintaining safe navigation even across wide ranges where obstacle influences spread.

Inventive Principle:
Principle #15Dynamics

3Reliability

If all possible paths are calculated to ensure safety, then collision avoidance is improved, but device complexity increases

Engineering Contradiction:
ImprovesafetyVSAvoidcalculation system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies partial action by calculating only the necessary portion of paths - specifically, paths that avoid static obstacles are pre-calculated, while dynamic obstacle avoidance is handled through real-time detection and localized path adjustment. This avoids the excessive complexity of calculating all possible paths while maintaining adequate safety.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS10102750B2Object path prediction method, apparatus, and program, and automatic operation system
Publication Date: 2018.10.16 TOYOTA JIDOSHA KK
  • US10102750B2 patent drawing
  • US10102750B2 patent drawing
  • US10102750B2 patent drawing

AI summary

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.