Zoe Doulgeri

Marios Kiatos, Iason Sarantopoulos, Sotiris Malassiotis et al.

Non-prehensile pushing actions have the potential to singulate a target object from its surrounding clutter in order to facilitate the robotic grasping of the target. To address this problem we utilize a heuristic rule that moves the target object towards the workspace's empty space and demonstrate that this simple heuristic rule achieves singulation. We incorporate this effective heuristic rule to the reward in order to train more efficiently reinforcement learning (RL) agents for singulation. Simulation experiments demonstrate that this insight increases performance. Finally, our results show that the RL-based policy implicitly learns something similar to one of the used heuristics in terms of decision making. Qualitative results, code, pre-trained models and simulation environments are available at https://github.com/robot-clutter/improved_rl.

Theodora Kastritsi, Zoe Doulgeri

The restriction of feasible motions of a manipulator link constrained to move through an entry port is a common problem in minimum invasive surgery procedures. Additional spatial restrictions are required to ensure the safety of sensitive regions from unintentional damage. In this work, we design a target admittance model that is proved to enforce robot tool manipulation by a human through a remote center of motion and to guarantee that the tool will never enter or touch forbidden regions. The control scheme is proved passive under the exertion of a human force ensuring manipulation stability, and smooth natural motion in hands-on surgical procedures enhancing the user's feeling of control over the task. Its performance is demonstrated by experiments with a setup mimicking a hands-on surgical procedure comprising a KUKA LWR4+ and a virtual intraoperative environment.

Dimitrios Papageorgiou, Leonidas Koutras, Zoe Doulgeri

In this work, a control scheme for approaching and unveiling a partially occluded object of interest is proposed.The control scheme is based only on the classified point cloud obtained by the in-hand camera attached to the robot's end effector. It is shown that the proposed controller reaches in the vicinity of the object progressively unveiling the neighborhood of each visible point of the object of interest. It can therefore potentially achieve the complete unveiling of the object. The proposed control scheme is evaluated through simulations and experiments with a UR5e robot with an in-hand RealSense camera on a mock-up vine setup for unveiling the stem of a grape.

Efi Psomopoulou, Nicholas Pestell, Fotios Papadopoulos et al.

This paper proposes a controller for stable grasping of unknown-shaped objects by two robotic fingers with tactile fingertips. The grasp is stabilised by rolling the fingertips on the contact surface and applying a desired grasping force to reach an equilibrium state. The validation is both in simulation and on a fully-actuated robot hand (the Shadow Modular Grasper) fitted with custom-built optical tactile sensors (based on the BRL TacTip). The controller requires the orientations of the contact surfaces, which are estimated by regressing a deep convolutional neural network over the tactile images. Overall, the grasp system is demonstrated to achieve stable equilibrium poses on various objects ranging in shape and softness, with the system being robust to perturbations and measurement errors. This approach also has promise to extend beyond grasping to stable in-hand object manipulation with multiple fingers.

Antonis Sidiropoulos, Yiannis Karayiannidis, Zoe Doulgeri

In this work, the problem of human-robot collaborative object transfer to unknown target poses is addressed. The desired pattern of the end-effector pose trajectory to a known target pose is encoded using DMPs (Dynamic Movement Primitives). During transportation of the object to new unknown targets, a DMP-based reference model and an EKF (Extended Kalman Filter) for estimating the target pose and time duration of the human's intended motion is proposed. A stability analysis of the overall scheme is provided. Experiments using a Kuka LWR4+ robot equipped with an ATI sensor at its end-effector validate its efficacy with respect to the required human effort and compare it with an admittance control scheme.

Antonis Sidiropoulos, Zoe Doulgeri

In this work, a novel Dynamic Movement Primitive (DMP) formulation is proposed which supports reversibility, i.e. backwards reproduction of a learned trajectory. Apart from sharing all favourable properties of the original DMP, decoupling the teaching of position and velocity profiles and bidirectional drivability along the encoded path are also supported. Original DMP have been extensively used for encoding and reproducing a desired motion pattern in several robotic applications. However, they lack reversibility, which is a useful and expedient property that can be leveraged in many scenarios. The proposed formulation is analyzed theoretically and its practical usefulness is showcased in an assembly by insertion experimental scenario.

Iason Sarantopoulos, Marios Kiatos, Zoe Doulgeri et al.

Extracting a known target object from a pile of other objects in a cluttered environment is a challenging robotic manipulation task encountered in many robotic applications. In such conditions, the target object touches or is covered by adjacent obstacle objects, thus rendering traditional grasping techniques ineffective. In this paper, we propose a pushing policy aiming at singulating the target object from its surrounding clutter, by means of lateral pushing movements of both the neighboring objects and the target object until sufficient 'grasping room' has been achieved. To achieve the above goal we employ reinforcement learning and particularly Deep Q-learning (DQN) to learn optimal push policies by trial and error. A novel Split DQN is proposed to improve the learning rate and increase the modularity of the algorithm. Experiments show that although learning is performed in a simulated environment the transfer of learned policies to a real environment is effective thanks to robust feature selection. Finally, we demonstrate that the modularity of the algorithm allows the addition of extra primitives without retraining the model from scratch.