Robotic Path Planning With Virtual Forces for Real-Time Obstacle Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing path planning algorithms for robotic devices are inefficient and computationally intensive, particularly in high-dimensional dynamic environments, and are not capable of real-time updates in response to moving obstacles and targets.
Innovation Solution
A method for real-time autonomous path planning that involves receiving telemetry data, encapsulating objects in a simulated robotic space, calculating movement directions based on virtual attractive, repulsive, and tangential forces, and converting these forces into torque vectors to define a path for the robotic device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional path planning algorithms are used to calculate optimal routes, then path optimality is improved, but computational efficiency deteriorates
Solution Approach 1:
The patent transforms the path planning problem from configuration space to task space, changing the dimensional perspective. Instead of planning in high-dimensional joint space (configuration space), the algorithm operates in lower-dimensional task space (end effector position and orientation), reducing computational complexity while maintaining path quality
Solution Approach 2:
The patent extracts only the essential components needed for path planning by using task space formulation. It separates the planning function from the full robot model, using only the relationship between joint angles and end effector position (Jacobian matrix) rather than complete dynamic models, thereby simplifying computations
2Manufacturing precision
If optimal path planning algorithms are used in static environments, then path accuracy is improved, but real-time adaptability deteriorates
Solution Approach 1:
The patent implements dynamic path planning by continuously updating the task space trajectory based on current robot state and environment. The algorithm recalculates virtual forces and adjusts the path in real-time as obstacles or targets move, enabling adaptation while maintaining accuracy through iterative optimization
Solution Approach 2:
The patent incorporates feedback mechanisms where the robot's current position, velocity, and acceleration are continuously monitored and fed back into the path planning algorithm. This feedback loop allows the system to adjust the planned path based on actual execution deviations and environmental changes, maintaining both accuracy and adaptability
3Power
If heavy computational components are launched into space, then processing capability is improved, but launch cost and system complexity deteriorate
Solution Approach 1:
The patent employs lightweight, low-cost onboard processors that perform sufficient path planning computations for space applications. Rather than relying on heavy Earth-based supercomputers, it uses simplified algorithms that can run efficiently on modest hardware, reducing launch mass and system complexity while providing adequate processing capability for autonomous operation
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided are a method, system, and non-transitory computer-readable medium for real-time autonomous path planning for a robotic device. The method includes receiving data about the robotic device in a three-dimensional workspace, encapsulating objects in the environment of the robotic device including the robotic device, a target, and one or more obstacles in simulated robotic space, calculating a direction of movement for the robotic device according to three virtual forces including a virtual attractive force, a virtual repulsive force, and a virtual tangential force acting at least partially perpendicularly relative to the virtual repulsive force, mapping each virtual force in the three-dimensional workspace into torque vectors in the simulated robotic space at each joint, converting a sum of the torque vectors into one or more commands for the robotic device defining a path to reach the target, and sending the one or more commands to the robotic device.