AI summary
Problem
Accurate environment modeling for safe robot motion planning is typically time-consuming, expensive, and reliant on costly external sensors or precise CAD files, which struggle with dynamic or frequently modified production environments.
Approach
The method records joint trajectories during exploratory motions, computes the swept volume of the robot links, and carves this volume out of a bounding box to generate a conservative 3D mesh of the unexplored or occupied space.
Key results
- Generates accurate conservative workspace meshes using only internal joint encoders
- Reduces modeling time to under seven minutes (three minutes exploration, four minutes computation)
- Enables reliable collision-free motion planning in a pick-and-place scenario
- Introduces a low-cost, passive exploration tool to accelerate workspace coverage
Why it matters
Provides a fast, sensor-free, and cost-effective alternative to traditional environment modeling, making safe autonomous robot deployment accessible to flexible manufacturing and Industry 4.0 settings.
Abstract
Generating a collision-free robot motion is crucial for safe applications in real-world settings. This requires an accurate model of all obstacle shapes within the constrained robot cell, which is particularly challenging and time-consuming. The difficulty is heightened in flexible production lines, where the environment model must be updated each time the robot cell is modified. Furthermore, sensor-based methods often necessitate costly hardware and calibration procedures, and can be influ- enced by environmental factors (e.g., light conditions or reflec- tions). To address these challenges, we present a novel data-driven approach to modeling a cluttered workspace, leveraging solely the robot’s internal joint encoders to capture exploratory motions. By computing the corresponding swept volume, we generate a (conservative) mesh of the environment that is subsequently used for collision checking within established path planning and control methods. Our method significantly reduces the complexity and cost of classical environment modeling by removing the need for CAD files and external sensors. We validate the approach with the KUKA LBR iisy collaborative robot in a pick-and-place scenario. In less than three minutes of exploratory robot motions and less than four additional minutes of computation time, we obtain an accurate model that enables collision-free motions. Our approach is intuitive, easy-to-use, making it accessible to users without specialized technical knowledge. It is applicable to all types of industrial robots or cobots.