Physical human-robot interfaces are a challenging aspect of exoskeleton design, mainly due to the fact that interfaces tend to migrate relatively to the body leading to discomfort and power losses. Therefore, the key is to develop interfaces that optimize attachment stiffness, i.e., reduce relative motion, without compromising comfort. To that end, we propose a method to obtain the optimal attachment pressure in terms of connection stiffness and comfort. The method is based on a soft robotic interface capable of actively controlling strapping pressure which is coupled to a cobot. Hereby the effects of strapping pressure on energetic losses, connection stiffness, and perceived comfort are analyzed. Results indicate a trade-off between connection stiffness and perceived comfort for this type of interface. An optimal strapping pressure was found in the 50 to 80 mmHg range. Connection stiffness was found to increase linearly over a pressure range from 0 mmHg (stiffness of 1139 N/m) to 100 mmHg (stiffness of 2232 N/m). And energetic losses were reduced by 42% by increasing connection stiffness. This research highlights the importance of strapping pressure when attaching an exoskeleton to a human and introduces a new adaptive interface to improve the coupling from an exoskeleton to an individual.

This paper presents a comparative analysis of six prominent registration techniques for solving CAD model alignment problems. Unlike the typical approach of assessing registration algorithms with synthetic datasets, our study utilizes point clouds generated from the Cranfield benchmark. Point clouds are sampled from existing CAD models and 3D scans of physical objects, introducing real-world complexities such as noise and outliers. The acquired point cloud scans, including ground-truth transformations, are made publicly available. This dataset includes several cleaned-up scans of nine 3D-printed objects. Our main contribution lies in assessing the performance of three classical (GO-ICP, RANSAC, FGR) and three learning-based (PointNetLK, RPMNet, ROPNet) methods on real-world scans, using a wide range of metrics. These include recall, accuracy and computation time. Our comparison shows a high accuracy for GO-ICP, as well as PointNetLK, RANSAC and RPMNet combined with ICP refinement. However, apart from GO-ICP, all methods show a significant number of failure cases when applied to scans containing more noise or requiring larger transformations. FGR and RANSAC are among the quickest methods, while GO-ICP takes several seconds to solve. Finally, while learning-based methods demonstrate good performance and low computation times, they have difficulties in training and generalizing. Our results can aid novice researchers in the field in selecting a suitable registration method for their application, based on quantitative metrics. Furthermore, our code can be used by others to evaluate novel methods.

Robotic manipulation in cluttered environments requires synergistic planning among prehensile and non-prehensile actions. Previous works on sampling-based Task and Motion Planning (TAMP) algorithms, e.g. PDDLStream, provide a fast and generalizable solution for multi-modal manipulation. However, they are likely to fail in cluttered scenarios where no collision-free grasping approaches can be sampled without preliminary manipulations. To extend the ability of sampling-based algorithms, we integrate a vision-based Reinforcement Learning (RL) non-prehensile procedure, pusher . The pushing actions generated by pusher can eliminate interlocked situations and make the grasping problem solvable. Also, the sampling-based algorithm evaluates the pushing actions by providing rewards in the training process, thus the pusher can learn to avoid situations leading to irreversible failures. The proposed hybrid planning method is validated on a cluttered bin-picking problem and implemented in both simulation and real world. Results show that the pusher can effectively improve the success ratio of the previous sampling-based algorithm, while the sampling-based algorithm can help the pusher learn pushing skills.

The assembly industry is shifting more towards customizable products, or requiring assembly of small batches. This requires a lot of reprogramming, which is expensive because a specialized engineer is required. It would be an improvement if untrained workers could help a cobot to learn an assembly sequence by giving advice. Learning an assembly sequence is a hard task for a cobot, because the solution space increases drastically when the complexity of the task increases. This work introduces a novel method where human knowledge is used to reduce this solution space, and as a result increases the learning speed. The method proposed is the IRL-PBRS method, which uses Interactive Reinforcement Learning (IRL) to learn from human advice in an interactive way, and uses Potential Based Reward Shaping (PBRS), in a simulated environment, to focus learning on a smaller part of the solution space. The method was compared in simulation to two other feedback strategies. The results show that IRL-PBRS converges more quickly to a valid assembly sequence policy and does this with the fewest human interactions. Finally, a use case is presented where participants were asked to program an assembly task. Here, the results show that IRL-PBRS learns quickly enough to keep up with advice given by a user, and is able to adapt online to a changing knowledge base.

Introduction: Active patient participation is crucial for effective robot-assisted rehabilitation. Quantifying the user's Active Level of Participation (ALP) during therapy and developing human-robot interaction strategies that promote engagement can improve rehabilitation outcomes. However, existing methods for estimating participation are often unimodal and do not provide continuous participation assessment.Methods: This study proposes a novel approach for estimating ALP during upper-limb robot-aided rehabilitation by leveraging machine learning within a multimodal framework. The system integrates pressure sensing at the human-robot interface and muscle activity monitoring to provide a more comprehensive assessment of user participation. The estimated ALP is used to dynamically adapt task execution time, enabling an adaptive ALP-driven impedance control strategy. The proposed approach was tested in a laboratory setting using a collaborative robot equipped with the sensorized interface. A comparative analysis was conducted against a conventional impedance controller, commonly used in robot-aided rehabilitation scenarios.Results: The results demonstrated that participants using the ALP-driven impedance control exhibited significantly higher positive mechanical work and greater muscle activation compared to the control group. Additionally, subjective feedback indicated increased engagement and confidence when interacting with the adaptive system.Discussion: Closing the robot's control loop by adapting to ALP effectively enhanced human-robot interaction and motivated participants to engage more actively in their therapy. These findings suggest that ALP-driven control strategies may improve user involvement in robot-assisted rehabilitation, warranting further investigation in clinically relevant settings.