AGV Safety Control Using Dynamic Obstacle Trajectory Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous robots are limited to static environments and cannot safely operate alongside humans due to their inability to detect and navigate around dynamic obstacles, leading to forced interruptions in motion and inefficiencies in task execution.
Innovation Solution
An autonomous robotic vehicle system equipped with a vehicle management system that uses sensors and computational resources to predict the trajectory of dynamic objects, allowing for real-time path optimization and obstacle avoidance, enabling safe and efficient operation in dynamic environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional safety mechanisms force the robotic vehicle to stop motion in the presence of unexpected moving objects, then safety is improved, but productivity and operational efficiency deteriorate due to forced interruptions
Solution Approach 1:
The system performs preliminary actions by predicting the future trajectories of moving objects using sensor data and machine learning models before collisions occur. This allows the navigation system to proactively plan avoidance paths rather than reactively stopping when obstacles are detected, thereby maintaining safety while reducing unnecessary interruptions to operational efficiency
Solution Approach 2:
The system dynamically adjusts the robotic vehicle's motion plan in real-time based on predicted trajectories of moving objects. Instead of static stop-and-go behavior, the navigation system continuously optimizes the path and velocity profile to safely navigate around predicted obstacle positions, enabling smooth adaptive motion that maintains both safety and productivity
2Device complexity
If conventional autonomous navigation robots are employed in static environments with fixed objects, then navigation simplicity is improved, but adaptability to dynamic environments deteriorates
Solution Approach 1:
The system continuously receives feedback from sensors detecting moving objects and their trajectories, and uses this feedback to dynamically adjust the navigation plan. The closed-loop control system processes real-time sensor data, updates predictions of obstacle movements, and modifies the robotic vehicle's path accordingly, enabling adaptation to dynamic environments while maintaining manageable navigation complexity through systematic feedback processing
Solution Approach 2:
The system replaces traditional mechanical obstacle avoidance methods with computational approaches using machine learning models and trajectory prediction algorithms. This substitution of mechanical reaction systems with intelligent prediction systems enables the robot to anticipate and adapt to dynamic obstacles without requiring complex mechanical sensing and response mechanisms
Data Source
AI summary
An autonomous robot system to enable flexible, safe, efficient, and automated movement of goods and materials in a dynamic environment including one or more dynamic objects (e.g., humans). The autonomous robot system includes a modular autonomous ground vehicle (AGV) including a vehicle management system having a safety management system. The safety management system includes one or more safety management controllers to perform safety functions to enable the modular AGV to operate safely and efficiently alongside humans in a dynamic environment (e.g., a warehouse or fulfillment facility).