Lars Tingelstad

Norwegian University of Science and Technology | NTNU · Department of Mechanical and Industrial Engineering

Diffusion models have been shown to excel in robotic imitation learning by mastering the challenge of modeling complex distributions. However, sampling speed has traditionally not been a priority due to their popularity for image generation, limiting their application to dynamical tasks. While recent work has improved the sampling speed of diffusio...

This article proposes the use of Geometric Dimensioning and Tolerancing (GD &T) information from STEP AP242 for robotic manufacturing applications. This information can be directly added to the relevant features of the 3D model as per Model Based Definition methodology during the design phase of the product life cycle. STEP AP242 neutral exchange f...

This article uses the Product Manufacturing Information (PMI) from STEP AP242 neutral files for gripper selection and grasp planning in a robotic assembly operation. The PMI, along with the part geometry and dimensions, are used in identifying various handling features of the parts and selecting an appropriate gripper. The required PMI, like materi...

This paper presents a novel procedure for robotic scanning of weld grooves in large tubular T-joints. The procedure is designed to record the discrete weld groove scans using a commercially available line laser scanner which is attached to the robot end-effector. The advantage of the proposed algorithm is that it does not require any prior knowledg...

A crane control system is proposed where the crane payload follows a desired position trajectory with ultimately bounded pendulum motion. The proposed control system includes a Lyapunov-based damping controller, which stabilizes the dynamics of the payload by increasing the damping of the pendulum motion. The crane with the resulting stabilized dyn...

This paper presents a novel weld groove parametrization algorithm, which is developed specifically for weld grooves in typical stub and butt joints between large tubular elements. The procedure is based on random sample consensus (RANSAC) with additionally proposed correction steps, including a corner correction step for grooves with narrow root we...

Line laser scanners are a sub-type of structured light 3D scanners that are relatively common devices to find within the industrial setting, typically in the context of assembly, process control, and welding. Despite its extensive use, scanning of some materials remain a difficult or even impossible task without additional pre-processing. For insta...

This article explores using aspects of STEP AP242 for constraint-based robot programming for assembly operations. Industry 4.0 envisions smart, connected factories where all the operations are connected by an unbroken thread of product and process data. As part of these efforts, many industries are adopting Model Based Definition and STEP AP242. ST...

In this paper, we present a novel system for controlling a KMR iiwa mobile robot using ROS2. The KMR iiwa is a mobile robot with a manipulator mounted on the base that is developed by the robot manufacturer KUKA. The developed system integrates with the Sunrise.OS operating system of the mobile robot and exposes sensor and control interfaces over U...

This paper presents a method for coarse alignment of point clouds by introducing a new descriptor based on the local curvature. The method is developed for model fitting a CAD model for use in robotic assembly. The method is based on selecting keypoints depending on shape factors calculated from the local covariance matrix of the surface. A descrip...

In this paper, we consider several parameterizations of rigid transformations using motors in 3-D conformal geometric algebra. In particular, we present parameterizations based on the exponential, outer exponential, and Cayley maps of bivectors, as well as a map based on a first-order approximation of the exponential followed by orthogonal projecti...

In this paper we present a novel method for nonlinear rigid body motion estimation from noisy data using heterogeneous sets of objects of the conformal model in geometric algebra. The rigid body motions are represented by motors. We employ state-of-the-art nonlinear optimization tools and compute gradients and Jacobian matrices using forward-mode a...

This paper presents an approach for detecting primitive geometric objects in point clouds captured from 3D cameras. Primitive objects are objects that are well defined with parameters and mathematical relations, such as lines, spheres and ellipsoids. RANSAC, a robust parameter estimator that classifies and neglects outliers, is used for object dete...

This paper presents an approach for initial alignment or coarse registration of a partial 3D point cloud of objects. The method is based on computing the centroid of the points in the point cloud, and a line derived from the surface normals. This approach uses conformal geometric algebra and non-linear least squares optimization to achieve the resu...

This thesis is on the estimation of rigid body motions from observations of points, lines, and planes in conformal geometric algebra using nonlinear least-squares optimization. Distance measures based on the ratio and difference of points, lines, and planes are formulated and analyzed. Then, the properties of these distance measures, such as transl...

In this work, we present a novel approach to non-linear optimization of multivectors in the Euclidean and conformal model of geometric algebra by introducing automatic differentiation. This is used to compute gradients and Jacobian matrices of multivector valued functions for use in non-linear optimization where the emphasis is on the estimation of...

This paper presents robotic assembly of aircraft engine components that cannot be assembled using traditional robotic assembly methods. The reason for this is uncertainty in shape and dimensional accuracy due to imperfections in the preceding manufacturing processes. In addition, the aircraft engine components are designed as complex geometry thin...

This paper presents an automated assembly and tack welding operation of high performance aerospace components using two real-time controlled industrial robots and a high-precision non-contact measurement system. The system was able to align two components with an offset distance less than 0.1 mm, well within manufacturing tolerances.

Design and performance measurements of a framework for external real-time trajectory generation for industrial robots is presented. The framework is implemented entirely in Python. It serves as a proof of concept for performing real-time trajectory generation in Python, from a PC with connection to the motion controller in an industrial robot contr...