Machine Collision Recovery Using Swept-Volume Motion Planning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manual recovery of machines after collisions is time-consuming and risky, especially for machines with complex kinematics or in cluttered environments, leading to prolonged downtime and potential damage.

Innovation Solution

An automated method for recovering a machine after collision with an object within the machine's environment, involving recording machine configurations, calculating swept volumes, and generating a recovery sequence of movements to return the machine to a safe position using motion planning algorithms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual recovery process is used by operator, then machine can be recovered to safe state, but recovery time is prolonged and operator safety is at risk

Engineering Contradiction:
Improvemachine recovery safetyVSAvoidrecovery time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system pre-calculates multiple recovery trajectories before a collision occurs, storing them as configuration sequences. When a collision happens, the system can immediately execute a pre-computed safe recovery path without requiring real-time manual intervention, thus reducing recovery time while maintaining safety

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The machine automatically recovers from collision using pre-calculated trajectories and automated control, eliminating the need for human operator intervention. The system monitors its own state, detects collisions, and executes recovery sequences autonomously, making the machine self-sufficient in the recovery process

Inventive Principle:
Principle #25Self-service

2Adaptability or versatility

If machine configuration is complex with high degrees of freedom, then machine can perform complicated tasks, but manual recovery becomes more complicated and time-consuming

Engineering Contradiction:
Improvemachine task capabilityVSAvoidrecovery operation complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

For machines with complex kinematics, the system pre-calculates recovery trajectories considering all degrees of freedom and mechanical constraints before operation. These pre-computed configuration sequences account for the complex kinematic chains, eliminating the need for operators to manually navigate complex recovery procedures

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual mechanical manipulation by operators with automated computational algorithms. Motion planning algorithms automatically compute recovery sequences for complex machines, substituting human operator actions with algorithmic control that can handle high-dimensional configuration spaces more efficiently

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If operator performs manual recovery, then machine can be recovered, but risk of causing further collisions increases

Engineering Contradiction:
Improvemachine recovery successVSAvoidrisk of further collisions
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system continuously monitors machine configuration and environmental obstacles during recovery, using feedback from sensors and pre-stored obstacle information. The motion planning algorithms adjust the recovery trajectory in real-time based on feedback, ensuring the machine moves along collision-free paths and preventing further collisions

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system pre-stores comprehensive obstacle information and pre-calculates collision-free recovery trajectories before recovery begins. By having obstacle data and safe paths prepared in advance, the system can guide the machine through recovery without risking new collisions, as the paths are pre-validated against known obstacles

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4644056A1Automatic collision recovery for machines
Publication Date: 2025.11.05 SIEMENS AG
  • EP4644056A1 patent drawingFigure 1
  • EP4644056A1 patent drawingFigure 2
  • EP4644056A1 patent drawingFigure 3

AI summary

Embodiments of the present disclosure provide a method and system for automatic recovery of a machine after a collision event occurred within a workspace environment of the machine. The method may comprise recording a plurality of configurations of a machine during execution of a task; calculating based on the plurality of recorded configurations, a swept volume occupied by the machine during execution of the task; in response to a collision event, determining, based on the swept volume, a recovery sequence of movements for the machine; and using the recovery sequence of movements to lead the machine back to a predefined known safe position after the collision event occurred.