Robotic systems often face challenges when attempting to grasp a target object due to interference from surrounding items. We propose a Deep Reinforcement Learning (DRL) method that develops joint policies for grasping and pushing, enabling effective manipulation of target objects within untrained, densely cluttered environments. In particular, a dual RL model is introduced, which presents high resilience in handling complicated scenes, reaching an average of 98% task completion in simulation and real-world scenes. To evaluate the proposed method, we conduct comprehensive simulation experiments in three distinct environments: densely packed building blocks, randomly positioned building blocks, and common household objects. Further, real-world tests are conducted using actual robots to confirm the robustness of our approach in various untrained and highly cluttered environments. The results from experiments underscore the superior efficacy of our method in both simulated and real-world scenarios, outperforming recent state-of-the-art methods. To ensure reproducibility and further the academic discourse, we make available a demonstration video, the trained models, and the source code for public access. https://sites.google.com/view/pushandgrasp/home.

Robotic teleoperation is used in various applications, including the nuclear industry, where the experience and intelligence of a human operator are necessary for making complex decisions that are beyond the autonomy of robots. Human-robot interfaces that help strengthen an operators situational awareness without inducing excessive cognitive load are crucial to the success of teleoperation. This paper presents a novel visual interface that allows operators to simultaneously control a 6-DoF camera platform and a robotic manipulator whilst experiencing the remote environment through a virtual reality head-mounted display (HMD). The proposed system, Orbital Head-Mounted Display (OHMD), utilizes head rotation tracking to command camera movement in azimuth and elevation directions around a fixation point located at a robot's end-effector. A human factor study was conducted to compare the interface acceptance, perceived workload, and task performance of OHMD with a conventional interface utilizing multiple fixed cameras (Array) and a standard head-mounted display implementation (HMD). Results show that both the OHMD and HMD interfaces significantly improve task performance, reduce perceived workload and increase interface acceptance compared to the Array interface. Participants reported they preferred OHMD due to the increased assistance and freedom in viewpoint selection. Whilst OHMD excelled in usefulness, the standard HMD interface allowed operators to perform robotic welding tasks significantly faster.

In tele-operation, haptic feedback from the remote environment to the human is often limited, which has been shown to negatively influence the performance and required time of tasks. The conventional research focus is on improving the quality of the haptic feedback (transparency), which may have led to significant improvement, but is still imperfect, with many unresolved issues. The present study presents an alternative approach to improve tele-operated tasks: by offering haptic shared control in which both operator and support system apply the required forces at the input (master) device. It is hypothesized that virtual forces from well-designed shared control will improve required time and accuracy, with less control effort, and that these benefits exist for perfect transparency but even more so for imperfect transparency. In an experimental study haptic shared control was designed to aid operators (n=9) with performing a simple bolt-spanner task using a planar (2D, 3DOF) tele-operator setup. The experimental results provided evidence for the hypotheses, showing that the tested tele-manipulation task benefits from haptic shared control, for three different levels of transparency. Essentially, the presence of haptic shared control allows for a worse transparency without compromising required time, and can even improve required time during perfect transparency.

The Cayley-Hamilton theorem is an important theorem of linear algebra which is well known and used in system theory. Unfortunately, this powerful result is practically never used in robotics even though it is of extreme relevance. This article is a review of the use of this result for the calculation of general matrix functions which are very common in robotics. It will be shown how any analytic matrix function like exponential, logarithm and more complicated expressions in robotics, can be easily and analytically calculated in an explicit form. Examples are given for the exponential map, inverse of the exponential map, and the derivative of the exponential map. For the first two examples there exist well known expressions in the literature, but the last one is not as easy to compute without the presented methods

This paper presents an elegant contact dynamics model in screw bondgraph form. It can model the contact between any two objects of finite curvature. It does so by defining a Gauss frame on the surfaces of both objects in the points that are closest to each other. Then it describes how the Gauss frames move as the objects move relative to each other. This is called the contact kinematics. The contact kinematics detect when two objects touch, then describe how they roll and slide over and along each other, and then detect when they get loose again. With the contact kinematics a dynamic screw bondgraph model is built. This dynamics model is verified in two simulations. The first simulation shows two objects of nontrivial curvature, eggs, rolling over each other. The second shows a robotic hand manipulating an object.

The Hermes Robot Arm (HERA) is a robot that will support the Hermes Spaceplane in its primary mission: the servicing of the Columbus Free Flyer. The emphasis is on the way HERA deals with the uncertainties in its environment, which measures and devices are introduced to ensure reliability and safety, and how to make sure that the design will actually work. The main tasks for HERA concern the external servicing of the Columbus Free Flying Laboratory: exchange of supplies and equipment boxes, inspection of the laboratory outer surfaces, and providing support to astronauts performing extravehicular activities.>