Search

Industrial insertion tasks are often performed repetitively with parts that are subject to tight tolerances and prone to breakage. Learning an industrial insertion policy in real is challenging as the collision between the parts and the environment can cause slippage or breakage of the part. In this paper, we present a safe self-supervised method to learn a visuo-tactile insertion policy that is robust to grasp pose variations. The method reduces human input and collisions between the part and the receptacle. The method divides the insertion task into two phases. In the first align phase, a tactile-based grasp pose estimation model is learned to align the insertion part with the receptacle. In the second insert phase, a vision-based policy is learned to guide the part into the receptacle. The robot uses force-torque sensing to achieve a safe self-supervised data collection pipeline. Physical experiments on the USB insertion task from the NIST Assembly Taskboard suggest that the resulting policies can achieve 45/45 insertion successes on 45 different initial grasp poses, improving on two baselines: (1) a behavior cloning agent trained on 50 human insertion demonstrations (1/45) and (2) an online RL policy (TD3) trained in real (0/45).

Folding garments reliably and efficiently is a long standing challenge in robotic manipulation due to the complex dynamics and high dimensional configuration space of garments. An intuitive approach is to initially manipulate the garment to a canonical smooth configuration before folding. In this work, we develop SpeedFolding, a reliable and efficient bimanual system, which given user-defined instructions as folding lines, manipulates an initially crumpled garment to (1) a smoothed and (2) a folded configuration. Our primary contribution is a novel neural network architecture that is able to predict pairs of gripper poses to parameterize a diverse set of bimanual action primitives. After learning from 4300 human-annotated and self-supervised actions, the robot is able to fold garments from a random initial configuration in under 120s on average with a success rate of 93%. Real-world experiments show that the system is able to generalize to unseen garments of different color, shape, and stiffness. While prior work achieved 3-6 Folds Per Hour (FPH), SpeedFolding achieves 30-40 FPH., Comment: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022

Robot learning of real-world manipulation tasks remains challenging and time consuming, even though actions are often simplified by single-step manipulation primitives. In order to compensate the removed time dependency, we additionally learn an image-to-image transition model that is able to predict a next state including its uncertainty. We apply this approach to bin picking, the task of emptying a bin using grasping as well as pre-grasping manipulation as fast as possible. The transition model is trained with up to 42000 pairs of real-world images before and after a manipulation action. Our approach enables two important skills: First, for applications with flange-mounted cameras, picks per hours (PPH) can be increased by around 15% by skipping image measurements. Second, we use the model to plan action sequences ahead of time and optimize time-dependent rewards, e.g. to minimize the number of actions required to empty the bin. We evaluate both improvements with real-robot experiments and achieve over 700 PPH in the YCB Box and Blocks Test., Comment: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)

We present Ruckig, an algorithm for Online Trajectory Generation (OTG) respecting third-order constraints and complete kinematic target states. Given any initial state of a system with multiple Degrees of Freedom (DoFs), Ruckig calculates a time-optimal trajectory to an arbitrary target state defined by its position, velocity, and acceleration limited by velocity, acceleration, and jerk constraints. The proposed algorithm and implementation allows three contributions: (1) To the best of our knowledge, we derive the first time-optimal OTG algorithm for arbitrary, multi-dimensional target states, in particular including non-zero target acceleration. (2) This is the first open-source prototype of time-optimal OTG with limited jerk and complete time synchronization for multiple DoFs. (3) Ruckig allows for directional velocity and acceleration limits, enabling robots to better use their dynamical resources. We evaluate the robustness and real-time capability of the proposed algorithm on a test suite with over 1,000,000,000 random trajectories as well as in real-world applications., Comment: Robotics: Science and Systems (RSS), 2021

Robot learning is often simplified to planar manipulation due to its data consumption. Then, a common approach is to use a fully-convolutional neural network to estimate the reward of grasp primitives. In this work, we extend this approach by parametrizing the two remaining, lateral Degrees of Freedom (DoFs) of the primitives. We apply this principle to the task of 6 DoF bin picking: We introduce a model-based controller to calculate angles that avoid collisions, maximize the grasp quality while keeping the uncertainty small. As the controller is integrated into the training, our hybrid approach is able to learn about and exploit the model-based controller. After real-world training of 27000 grasp attempts, the robot is able to grasp known objects with a success rate of over 92% in dense clutter. Grasp inference takes less than 50ms. In further real-world experiments, we evaluate grasp rates in a range of scenarios including its ability to generalize to unknown objects. We show that the system is able to avoid collisions, enabling grasps that would not be possible without primitive adaption., Comment: 2021 IEEE International Conference on Robotics and Automation (ICRA)

Despite its utopian promises as a disruptive equalizer, AI - like most tools deployed under the guise of neutrality - has tended to simply reinforce existing social structures. To counter this trend, radical AI calls for centering on the marginalized. We argue that gaps in key infrastructure are preventing the widespread adoption of radical AI, and propose a guiding principle for both identifying these infrastructure gaps and evaluating whether proposals for new infrastructure effectively center marginalized voices., Comment: 4 pages, Accepted at the Resistance AI Workshop @ NeurIPS 2020

Flexible pick-and-place is a fundamental yet challenging task within robotics, in particular due to the need of an object model for a simple target pose definition. In this work, the robot instead learns to pick-and-place objects using planar manipulation according to a single, demonstrated goal state. Our primary contribution lies within combining robot learning of primitives, commonly estimated by fully-convolutional neural networks, with one-shot imitation learning. Therefore, we define the place reward as a contrastive loss between real-world measurements and a task-specific noise distribution. Furthermore, we design our system to learn in a self-supervised manner, enabling real-world experiments with up to 25000 pick-and-place actions. Then, our robot is able to place trained objects with an average placement error of 2.7 (0.2) mm and 2.6 (0.8){\deg}. As our approach does not require an object model, the robot is able to generalize to unknown objects while keeping a precision of 5.9 (1.1) mm and 4.1 (1.2){\deg}. We further show a range of emerging behaviors: The robot naturally learns to select the correct object in the presence of multiple object types, precisely inserts objects within a peg game, picks screws out of dense clutter, and infers multiple pick-and-place actions from a single goal state., Comment: Published in the IEEE Robotics and Automation Letters

Robotic grasping in cluttered environments is often infeasible due to obstacles preventing possible grasps. Then, pre-grasping manipulation like shifting or pushing an object becomes necessary. We developed an algorithm that can learn, in addition to grasping, to shift objects in such a way that their grasp probability increases. Our research contribution is threefold: First, we present an algorithm for learning the optimal pose of manipulation primitives like clamping or shifting. Second, we learn non-prehensible actions that explicitly increase the grasping probability. Making one skill (shifting) directly dependent on another (grasping) removes the need of sparse rewards, leading to more data-efficient learning. Third, we apply a real-world solution to the industrial task of bin picking, resulting in the ability to empty bins completely. The system is trained in a self-supervised manner with around 25000 grasp and 2500 shift actions. Our robot is able to grasp and file objects with 274 picks per hour. Furthermore, we demonstrate the system's ability to generalize to novel objects., Comment: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)

Given the task of learning robotic grasping solely based on a depth camera input and gripper force feedback, we derive a learning algorithm from an applied point of view to significantly reduce the amount of required training data. Major improvements in time and data efficiency are achieved by: Firstly, we exploit the geometric consistency between the undistorted depth images and the task space. Using a relative small, fully-convolutional neural network, we predict grasp and gripper parameters with great advantages in training as well as inference performance. Secondly, motivated by the small random grasp success rate of around 3%, the grasp space was explored in a systematic manner. The final system was learned with 23000 grasp attempts in around 60h, improving current solutions by an order of magnitude. For typical bin picking scenarios, we measured a grasp success rate of 96.6%. Further experiments showed that the system is able to generalize and transfer knowledge to novel objects and environments., Comment: Accepted for ICRA 2019

High power pulsed magnetron sputtering (HPPMS) plasmas are pulsed discharges where the plasma composition as well as the fluxes and energies of ions are changing during the pulse. The time resolved energy distribution for Ar$^{1+}$ ions was measured and Phase Resolved Optical Emission Spectroscopy (PROES) for the Ar I line at 760 nm was done to get more insight in the transport properties of the plasma forming noble gas. These measurements were performed during HPPMS of titanium with argon at 0.5 Pa. The peak power density during the 50 $\mu$s pulses was 1.8 kW/cm$^2$. In this contribution we demonstrate how time resolved mass spectrometry and ICCD cameras can be used to shed more light on energy and particle transport in HPPMS-plasmas., Comment: The manuscript was submitted to the 7th Triennial Special Issue of the IEEE Transactions on Plasma Science "Images in Plasma Science," scheduled for publication in September 2014. The manuscript length is limited to 2 pages!

Plug-in hybrid electric vehicles (PHEVs) are an environmentally friendly technology that is expected to rapidly penetrate the transportation system. Renewable energy sources such as wind and solar have received considerable attention as clean power options for future generation expansion. However, these sources are intermittent and increase the uncertainty in the ability to generate power. The deployment of PHEVs in a vehicle-to-grid (V2G) system provide a potential mechanism for reducing the variability of renewable energy sources. For example, PHEV supporting infrastructures like battery exchange stations that provide battery service to PHEV customers could be used as storage devices to stabilize the grid when renewable energy production is fluctuating. In this paper, we study how to best site these stations in terms of how they can support both the transportation system and the power grid. To model this problem we develop a two-stage stochastic program to optimally locate the stations prior to the realization of battery demands, loads, and generation capacity of renewable power sources. We develop two test cases to study the benefits and the performance of these systems., Comment: Submitted to IEEE-SmartGridComm2010