Learning from Demonstrations(LfD) enables robots to acquire complex skills by observing human behavior, significantly reducing the need for explicit programming. However, applying LfD in industrial settings remains challenging due to limited demonstrations, variability in task executions, and the need to generalize across diverse scenarios. To address these issues, this paper presents a learning based hierarchical task and motion planning framework that integrates Behavior Trees (BT) for high-level task sequencing and Dynamic Motion Primitives (DMP) for low-level motion generation. Demonstration trajectories are segmented and actions are generated using an agentcentric, state-augmented segmentation strategy. Subsequently, relevant features are automatically extracted to define the pre-and post-conditions for each action for the construction of a modular BT. For motion execution, DMP are enhanced with a recovery mechanism for adaptive, obstacle-aware reproduction. A backchaining mechanism is also introduced for BT extension. Validation was performed through simulation and real-world experiments on multiple tasks. Comparative results demonstrate that the proposed method outperforms existing LfD and planning baselines in task success rate, efficiency, and motion smoothness, highlighting its potential for flexible and scalable automation.

Rescue robotics sets high requirements to perception algorithms due to the unstructured and potentially vision-denied environments. Pivoting Frequency-Modulated Continuous Wave radars are an emerging sensing modality for SLAM in this kind of environment. However, the complex noise characteristics of radar SLAM makes, particularly indoor, applications computationally demanding and slow. In this work, we introduce a novel radar SLAM framework, RaNDT SLAM, that operates fast and generates accurate robot trajectories. The method is based on the Normal Distributions Transform augmented by radar intensity measures. Motion estimation is based on fusion of motion model, IMU data, and registration of the intensity-augmented Normal Distributions Transform. We evaluate RaNDT SLAM in a new benchmark dataset and the Oxford Radar RobotCar dataset. The new dataset contains indoor and outdoor environments besides multiple sensing modalities (LiDAR, radar, and IMU).

People with disabilities (PwD) have the right to equal participation in the labor market under the 2008 Convention on the Rights of Persons with Disabilities [1], yet OECD data indicates that PwD remain excluded, with a 15% unemployment rate in 2019 across 32 OECD countries, and an 8.6% higher unemployment rate compared to people without disabilities [2]. With the growth of the elderly population and, consequently PwD, employers will face labor shortages [3]. The European Commission advocates for technology, like human-robot collaboration, to create ergonomic workplaces adapted to individual needs, aiming to enhance PwD inclusion and alleviate labor shortages [4].

As labor shortage is rising at an alarming rate, it is imperative to enable all people to work, particularly people with disabilities and elderly people. Robots are often used as universal tool to assist people with disabilities. However, for such human-robot workstations universal design fails. We mitigate the challenges of selecting an individualized set of input and output devices by matching devices required by the work process and individual disabilities adhering to the Convention on the Rights of Persons with Disabilities passed by the United Nations. The objective is to facilitate economically viable work-stations with just the required devices, hence, lowering overall cost of corporate inclusion and during redesign of workplaces. Our work focuses on developing an efficient approach to filter input and output devices based on a person's disabilities, resulting in a tailored list of usable devices. The methodology enables an automated assessment of devices compatible with specific disabilities defined in International Classification of Functioning, Disability and Health. In a mock-up, we showcase the synthesis of input and output devices from disabilities, thereby providing a practical tool for selecting devices for individuals with disabilities.

Cyber-Physical Systems constitute one of the core concepts in Industry 4.0 aiming at realizing production systems that combine the efforts of human workers, robots, and intelligent entities. This is particularly crucial in Human-Robot Collaboration manufacturing where a tight peer-to-peer interaction between humans and intelligent autonomous robots is necessary. The work proposes the integration of novel Artificial Intelligence technologies to enhance the flexibility and adaptability of collaborative robots. The integrated functionalities allow a collaborative robot to autonomously recognize the tasks a human worker performs, and accordingly adapt its behavior. The approach is deployed on a real HRC scenario showing the functioning of the developed cognitive capabilities and the increased flexibility of resulting collaborations.

This contribution demonstrates the usage of fold-based joints to create a novel 3 DoF 3R(RPaR) parallel robot design. Multiple folding mechanisms are introduced, fulfilling the function of revolute, prismatic, and spherical joints. Folding mechanisms are here tested regarding their applicability in parallel kinematic robots taking advantage of beneficial properties such as increased stiffness, flat-foldability and compressed states, easy cleaning as well as lightweight designs. The designed delta robot structure is then analysed for its motion behaviour, workspace dimensions and validated by a 3D printed model. Further, scalability possibilities are presented.

Safety is a central challenge in human-robot collaboration. Particularly in higher collaboration levels, separating safety devices, such as fences, are no longer needed and must be replaced by intelligent sensor-based systems. Of particular interest is the adaptive speed control of the robot. This work presents a methodology to adaptively control the end-effector velocity of the robot based on the distances to dynamic environmental objects. The method combines distance measurement and environmental subtraction with conservative velocity estimation using robot-specific stopping distances and is available in real-time. Data acquisition is performed using a co-moving 3D camera sensor attached to the robot structure.

Human-robot collaboration offers the advantage of combining human characteristics and robotic capabilities, balancing individual weaknesses. In the inclusive project Next Generation, we are exploring the possibility of using collaborative robots as assistive devices for people with severe and multiple disabilities. An important step in implementing an inclusive workstation with a collaborative robot is determining the level of assistance required. Therefore, we developed a novel methodology and a capability-based software tool to determine the individual level of challenge. In this paper, we present the developed tool and its validation. We validate the methodology and tool using an industrial sample application from first labor market incorporating participants with varying mental and physical disabilities.

A novel 2-RER reconfigurable parallel mechanism (ReConBot) considered as the flexible torso of the mobile manipulator is proposed. This paper deals with the analysis of reconfiguration, kinematics, and motion planning. The ReConBot is composed of straight bar-shape base and moving platforms and two metamorphic kinematic chains (MKC) consisted of a revolute (R) joint, a planar (E) joint, and an R joint in sequence. Firstly, mobility and reconfiguration analysis discuss the conditions and mutual mode transition rules of 12 possible configuration states. And then, the kinematics model covers all states with Cartesian coordinate and axis/angle representations. What's more, the motion planning following the rules of the mode transition is explained and illustrated together with a case study. Furthermore, the method of handling the transition at singularity position is discussed. Finally, the robotic system and its experiments verify the correctness of the theoretical analysis and the validation of reconfiguration rules.

The increasing energy consumption within the industrial sector causes great concerns among numerous countries. Accordingly, an extensive reorientation towards an energy-efficient facility and processes design is essential for innovative production systems. In terms of automated object manipulation, energy efficiency significantly is affected by the physical design as well as by the dynamic characteristics of the manipulator. Since the influence on physical design parameters often is limited, a great impact on energy-efficiency of innovative manufacturing systems may result from an intelligent task management and suitable motion strategies. This contribution identifies energy-efficiency potentials for industrial manipulators in terms of motion design and redundant actuator configurations. In this context, an efficient trajectory planning algorithm is proposed, estimating the energy demand of object manipulation tasks in consideration of dynamic motion parameters as well as redundant actuator configurations. For this purpose, the geometric path as well as the motion law of given trajectories are optimized by a spatial displacement of predefined nodes and by an adjustment of corresponding time intervals. In order to verify its generality, the presented method is applied to the spatial n-PRPaR manipulator exhibiting actuation redundancy. According results show a significant energy reduction, establishing high potentials for an increased efficiency of industrial robots.

Precision is an important feature in modern robotics and manipulation technology. Elevation of the robot's end-effector precision depends on different features as stiffness, tolerance etc. which should be considered during the synthesis and design phase of the manipulator. The focus of this study is on the structural stiffness of parallel kinematic manipulators (PKM) exhibiting actuation redundancy. It is determined how the stiffness depends on physical and geometrical characteristics of the manipulator and how it is possible to take advantage of redundancy to enhance the stiffness of the manipulator. It is shown that redundantly actuated PKM (RA-PKM) with components made of softer and accordingly lighter materials demonstrate comparable stiffness to the non-redundant manipulators which consequently decrease the required energy for moving the dead-load in operation. Based on the model built in this study, optimizations are conducted and manipulators with optimal morphologies for different tasks are introduced. As a case study, RA-PKM of type n-R RPaRs are considered.

Spatial object manipulation is typically accomplished by parallel kinematic manipulators (PKM), whose number of actuators is equal to the required number of degrees of freedom. In order to improve the performance and reliability of PKM, their basic configuration can be extended by redundant actuators. This paper is devoted to the special case of PKM with both linear and rotational actuation, which can be operated simultaneously. Corresponding manipulators face the problem of coexisting translational and rotational joint space parameters inducing inhomogeneous Jacobian matrices. In this context, power manipulability ellipsoids provide a suitable performance evaluation for PKM featuring different types of redundantly applicable actuators. Accordingly, this research intends to analyze the kinetostatic performance of redundantly actuated PKM and to demonstrate their efficiency in contrast to non-redundant drive configurations. The analyses exemplarily are focused on the translational 3-RPC manipulator, since it can be equipped with both revolute and/or prismatic joint actuation.

Due to excellent dynamic properties and high precision, parallel manipulators are particularly suited for high-speed and high-accuracy object handling. For this reason, the design process of parallel manipulators is usually supposed to optimize the manipulators' dexterity or structural stiffness. Accordingly, this research intends to analyze the effects of changing actuator and frame-configurations regarding the handling performance of a class of translational 3-RPC-manipulators. Since the RPC-structure can be arranged with translational and/or rotational actuators, several different drive configurations are possible. Additionally, four different frame configurations can be identified, expanding the number of possible manipulators. In order to find an optimized actuator and frame configuration for a given task, this research approach systematically reduces the number of possible configurations by means of validity detection and kinetostatic performance analysis. Hence, it is shown that good performance can be achieved for all frame configurations by selecting a suitable actuator combination.

As a result of high precision and excellent dynamic properties parallel kinematic machines (PKM) are particularly suited for high-speed and high-accuracy object handling. To optimize the design of such PKM, only kinetostatic analysis is not sufficient. Additionally, dynamic properties should be taken into account. Hence, this research develops the dynamic model for a class of translational 3-RPC-manipulators with either pure prismatic joint or pure revolute joint actuation. For a given task the dynamic performance is compared to results of the kinetostatic analysis. Hence, it is shown that the dynamic properties highly influence the performance of the RPC-structure.

This work deals with the control design and control simulation for a parallel structure with reduced degrees of freedom. Firstly, a novel coupled PD-control algorithm which yields uniform eigenfrequencies and properties in all directions of motion is introduced. The results of the linear model are compared to automated MBS-simulations. Afterwards, the stability range is compared to the actual measured stability range which is much smaller. Elasticity effects due to the platform and the joint stiffness are implemented in the MBS-model and evaluated. In the last step, we compare the simulated stability regions of the updated MBS-models to the measured boundaries.