Surface Defect Identification using Bayesian Filtering on a 3D Mesh

This paper presents a CAD-based approach for automated surface defect detection. We leverage the a-priori knowledge embedded in a CAD model and integrate it with point cloud data acquired from commercially available stereo and depth cameras. The proposed method first transforms the CAD model into a high-density polygonal mesh, where each vertex represents a state variable in 3D space. Subsequently, a weighted least squares algorithm is employed to iteratively estimate the state of the scanned workpiece based on the captured point cloud measurements. This framework offers the potential to incorporate information from diverse sensors into the CAD domain, facilitating a more comprehensive analysis. Preliminary results demonstrate promising performance, with the algorithm achieving convergence to a sub-millimeter standard deviation in the region of interest using only approximately 50 point cloud samples. This highlights the potential of utilising commercially available stereo cameras for high-precision quality control applications.

Reactive Robot Navigation Using Quasi-conformal Mappings and Control Barrier Functions

This paper presents a robot control algorithm suitable for safe reactive navigation tasks in cluttered environments. The proposed approach consists of transforming the robot workspace into the \emph{ball world}, an artificial representation where all obstacle regions are closed balls. Starting from a polyhedral representation of obstacles in the environment, obtained using exteroceptive sensor readings, a computationally efficient mapping to ball-shaped obstacles is constructed using quasi-conformal mappings and M\"obius transformations. The geometry of the ball world is amenable to provably safe navigation tasks achieved via control barrier functions employed to ensure collision-free robot motions with guarantees both on safety and on the absence of deadlocks. The performance of the proposed navigation algorithm is showcased and analyzed via extensive simulations and experiments performed using different types of robotic systems, including manipulators and mobile robots.

MeshDMP: Motion Planning on Discrete Manifolds using Dynamic Movement Primitives

An open problem in industrial automation is to reliably perform tasks requiring in-contact movements with complex workpieces, as current solutions lack the ability to seamlessly adapt to the workpiece geometry. In this paper, we propose a Learning from Demonstration approach that allows a robot manipulator to learn and generalise motions across complex surfaces by leveraging differential mathematical operators on discrete manifolds to embed information on the geometry of the workpiece extracted from triangular meshes, and extend the Dynamic Movement Primitives (DMPs) framework to generate motions on the mesh surfaces. We also propose an effective strategy to adapt the motion to different surfaces, by introducing an isometric transformation of the learned forcing term. The resulting approach, namely MeshDMP, is evaluated both in simulation and real experiments, showing promising results in typical industrial automation tasks like car surface polishing.

An Anatomy-Aware Shared Control Approach for Assisted Teleoperation of Lung Ultrasound Examinations

The introduction of artificial intelligence and robotics in telehealth is enabling personalised treatment and supporting teleoperated procedures such as lung ultrasound, which has gained attention during the COVID-19 pandemic. Although fully autonomous systems face challenges due to anatomical variability, teleoperated systems appear to be more practical in current healthcare settings. This paper presents an anatomy-aware control framework for teleoperated lung ultrasound. Using biomechanically accurate 3D models such as SMPL and SKEL, the system provides a real-time visual feedback and applies virtual constraints to assist in precise probe placement tasks. Evaluations on five subjects show the accuracy of the biomechanical models and the efficiency of the system in improving probe placement and reducing procedure time compared to traditional teleoperation. The results demonstrate that the proposed framework enhances the physician's capabilities in executing remote lung ultrasound examinations, towards more objective and repeatable acquisitions.

A Passivity-Based Variable Impedance Controller for Incremental Learning of Periodic Interactive Tasks

In intelligent manufacturing, robots are asked to dynamically adapt their behaviours without reducing productivity. Human teaching, where an operator physically interacts with the robot to demonstrate a new task, is a promising strategy to quickly and intuitively reconfigure the production line. However, physical guidance during task execution poses challenges in terms of both operator safety and system usability. In this paper, we solve this issue by designing a variable impedance control strategy that regulates the interaction with the environment and the physical demonstrations, explicitly preventing at the same time passivity violations. We derive constraints to limit not only the exchanged energy with the environment but also the exchanged power, resulting in smoother interactions. By monitoring the energy flow between the robot and the environment, we are able to distinguish between disturbances (to be rejected) and physical guidance (to be accomplished), enabling smooth and controlled transitions from teaching to execution and vice versa. The effectiveness of the proposed approach is validated in wiping tasks with a real robotic manipulator.

Direct Imitation Learning-based Visual Servoing using the Large Projection Formulation

Today robots must be safe, versatile, and user-friendly to operate in unstructured and human-populated environments. Dynamical system-based imitation learning enables robots to perform complex tasks stably and without explicit programming, greatly simplifying their real-world deployment. To exploit the full potential of these systems it is crucial to implement closed loops that use visual feedback. Vision permits to cope with environmental changes, but is complex to handle due to the high dimension of the image space. This study introduces a dynamical system-based imitation learning for direct visual servoing. It leverages off-the-shelf deep learning-based perception backbones to extract robust features from the raw input image, and an imitation learning strategy to execute sophisticated robot motions. The learning blocks are integrated using the large projection task priority formulation. As demonstrated through extensive experimental analysis, the proposed method realizes complex tasks with a robotic manipulator.

Towards Robotised Palpation for Cancer Detection through Online Tissue Viscoelastic Characterisation with a Collaborative Robotic Arm

This paper introduces a new method for estimating the penetration of the end effector and the parameters of a soft body using a collaborative robotic arm. This is possible using the dimensionality reduction method that simplifies the Hunt-Crossley model. The parameters can be found without a force sensor thanks to the information of the robotic arm controller. To achieve an online estimation, an extended Kalman filter is employed, which embeds the contact dynamic model. The algorithm is tested with various types of silicone, including samples with hard intrusions to simulate cancerous cells within a soft tissue. The results indicate that this technique can accurately determine the parameters and estimate the penetration of the end effector into the soft body. These promising preliminary results demonstrate the potential for robots to serve as an effective tool for early-stage cancer diagnostics.

Safe Execution of Learned Orientation Skills with Conic Control Barrier Functions

In the field of Learning from Demonstration (LfD), Dynamical Systems (DSs) have gained significant attention due to their ability to generate real-time motions and reach predefined targets. However, the conventional convergence-centric behavior exhibited by DSs may fall short in safety-critical tasks, specifically, those requiring precise replication of demonstrated trajectories or strict adherence to constrained regions even in the presence of perturbations or human intervention. Moreover, existing DS research often assumes demonstrations solely in Euclidean space, overlooking the crucial aspect of orientation in various applications. To alleviate these shortcomings, we present an innovative approach geared toward ensuring the safe execution of learned orientation skills within constrained regions surrounding a reference trajectory. This involves learning a stable DS on SO(3), extracting time-varying conic constraints from the variability observed in expert demonstrations, and bounding the evolution of the DS with Conic Control Barrier Function (CCBF) to fulfill the constraints. We validated our approach through extensive evaluation in simulation and showcased its effectiveness for a cutting skill in the context of assisted teleoperation.

Elasticity Measurements of Expanded Foams using a Collaborative Robotic Arm

Medical applications of robots are increasingly popular to objectivise and speed up the execution of several types of diagnostic and therapeutic interventions. Particularly important is a class of diagnostic activities that require physical contact between the robotic tool and the human body, such as palpation examinations and ultrasound scans. The practical application of these techniques can greatly benefit from an accurate estimation of the biomechanical properties of the patient's tissues. In this paper, we evaluate the accuracy and precision of a robotic device used for medical purposes in estimating the elastic parameters of different materials. The measurements are evaluated against a ground truth consisting of a set of expanded foam specimens with different elasticity that are characterised using a high-precision device. The experimental results in terms of precision are comparable with the ground truth and suggest future ambitious developments.

Scalable and Efficient Continual Learning from Demonstration via Hypernetwork-generated Stable Dynamics Model

Learning from demonstration (LfD) provides an efficient way to train robots. The learned motions should be convergent and stable, but to be truly effective in the real world, LfD-capable robots should also be able to remember multiple motion skills. Multi-skill retention is a capability missing from existing stable-LfD approaches. On the other hand, recent work on continual-LfD has shown that hypernetwork-generated neural ordinary differential equation solvers, can learn multiple LfD tasks sequentially, but this approach lacks stability guarantees. We propose an approach for stable continual-LfD in which a hypernetwork generates two networks: a trajectory learning dynamics model, and a trajectory stabilizing Lyapunov function. The introduction of stability not only generates stable trajectories but also greatly improves continual learning performance, especially in the size-efficient chunked hypernetworks. With our approach, we can continually train a single model to predict the position and orientation trajectories of the robot's end-effector simultaneously for multiple real world tasks without retraining on past demonstrations. We also propose stochastic regularization with a single randomly sampled regularization term in hypernetworks, which reduces the cumulative training time cost for $N$ tasks from $\mathcal{O}(N^2)$ to $\mathcal{O}(N)$ without any loss in performance in real-world tasks. We empirically evaluate our approach on the popular LASA dataset, on high-dimensional extensions of LASA (including up to 32 dimensions) to assess scalability, and on a novel extended robotic task dataset (RoboTasks9) to assess real-world performance. In trajectory error metrics, stability metrics and continual learning metrics our approach performs favorably, compared to other baselines. Code and datasets will be shared after submission.