Mobile Robot Trajectory Planning Using Future Occupancy Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous robots face challenges in navigating environments safely due to the inability to effectively predict and avoid both static and dynamic obstacles, leading to potential collisions and inefficient path planning.
Innovation Solution
The development of a predictive model using occupancy maps and machine learning techniques, such as deep neural networks, to forecast the movement of dynamic obstacles, allowing the robot to plan trajectories that minimize collision risks and optimize path planning based on travel costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional obstacle avoidance methods are used, then the robot can navigate static obstacles, but it cannot effectively predict and avoid dynamic obstacles, leading to potential collisions
Solution Approach 1:
The system performs preliminary actions by generating occupancy maps at multiple time steps and using a predictive model to forecast future obstacle locations before the robot reaches them. This allows the robot to plan trajectories in advance that avoid predicted obstacle positions, rather than reacting to obstacles only when detected in real-time.
Solution Approach 2:
The system transitions from static obstacle avoidance to dynamic prediction by using a predictive model that processes occupancy maps across multiple time steps. The model learns and adapts to the dynamic behavior patterns of obstacles, enabling the robot to handle moving obstacles effectively while maintaining reliable collision avoidance.
2Reliability
If the robot plans paths avoiding all obstacles, then collision risk is minimized, but the path planning becomes inefficient and more complex
Solution Approach 1:
The system applies partial action by focusing computational resources on predicting and avoiding only those obstacles that pose actual collision risks, rather than treating all occupied cells equally. The predictive model identifies relevant dynamic obstacles and generates trajectories that specifically address these threats, reducing unnecessary planning complexity while maintaining safety.
3Productivity
If the robot uses a predictive model to forecast obstacle movements, then path planning efficiency is improved, but the computational requirements and system complexity increase
Solution Approach 1:
The system introduces an intermediary component - the predictive model that processes occupancy maps and generates future obstacle location predictions. This intermediary translates complex sensor data and obstacle behavior patterns into simplified trajectory guidance, improving path planning efficiency while managing computational complexity through modular architecture.
Data Source
AI summary
This specification describes trajectory planning for robotic devices. A robotic navigation system can obtain, for each of multiple time steps, data representing an environment of a robot at the time step. The system generates a series of occupancy maps for the multiple time steps, and uses the series of occupancy maps to determine occupancy predictions for one or more future time steps. Each occupancy prediction can identify predicted locations of obstacles in the environment of the robot at a different one of the future time steps. A planned trajectory can be determined for the robot using the occupancy predictions, and the robot initiates travel along the planned trajectory.