Robotic Trajectory Planning Using Real-Time Object Metrics

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Robotic systems face challenges in efficiently picking and moving objects with unknown dimensions or properties, as measurements are often taken after the object is lifted, leading to potential dropping or collision risks.

Innovation Solution

A combination of sensors, including depth sensors and force-torque sensors, is used to determine object metrics in real-time, allowing for preplanned and adaptive trajectory planning to ensure safe and efficient transport.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If measurements are taken after the object is lifted, then the robotic system can handle objects with unknown dimensions, but the risk of dropping or collision increases

Engineering Contradiction:
Improveability to handle objects with unknown dimensionsVSAvoidrisk of dropping or collision
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary measurements of object dimensions and properties using sensors (depth sensors, force-torque sensors, vision systems) before the robotic arm lifts the object. This allows the trajectory planning system to precalculate safe motion paths that account for the specific object characteristics, eliminating the need to measure after lifting and thereby preventing dropping or collision risks.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If real-time measurements are used for trajectory planning, then the safety and efficiency of object transport is improved, but the system complexity increases

Engineering Contradiction:
Improvesafety of object transportVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system divides the measurement and control process into separate modular components: depth sensors for dimensional measurement, force-torque sensors for weight and grip force monitoring, vision systems for object identification, and a trajectory planning module that processes sensor data. This segmentation allows each component to specialize in specific tasks, improving overall safety while making the complex system more manageable and maintainable.

Inventive Principle:
Principle #1Segmentation

3Measurement precision

If multiple sensors are used to determine object metrics, then the measurement precision is improved, but the device complexity increases

Engineering Contradiction:
Improveobject metrics measurement accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system integrates multiple sensor types (depth sensors, force-torque sensors, vision systems) into a unified measurement framework where sensor data is fused to comprehensively determine object dimensions, weight, and other metrics. This merging approach achieves high measurement precision by compensating for individual sensor limitations while the integrated architecture reduces overall complexity compared to separate independent systems.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3854535B1Real-time determination of object metrics for trajectory planning
Publication Date: 2026.03.11 GDM HOLDING LLC
  • EP3854535B1 patent drawingFigure 1A
  • EP3854535B1 patent drawingFigure 1B
  • EP3854535B1 patent drawingFigure 2A

AI summary

Example systems and methods may be used to determine a trajectory for moving an object using a robotic device. One example method includes determining a plurality of possible trajectories for moving an object with an end effector of a robotic manipulator based on a plurality of possible object measurements. The method may further include causing the robotic manipulator to pick up the object with the end effector. After causing the robotic manipulator to pick up the object with the end effector, the method may also include receiving sensor data from one or more sensors indicative of one or more measurements of the object. Based on the received sensor data, the method may additionally include selecting a trajectory for moving the object from the plurality of possible trajectories. The method may further include causing the robotic manipulator to move the object through the selected trajectory.