Search for: All records

The injection of laboratory animals with pathogenic microorganisms poses a significant safety risk because of the potential for injury by accidental needlestick. This is especially true for researchers using invertebrate models of disease due to the required precision and accuracy of the injection. The restraint of the greater wax moth larvae (Galleria mellonella) is often achieved by grasping a larva firmly between finger and thumb. Needle resistant gloves or forceps can be used to reduce the risk of a needlestick but can result in animal injury, a loss of throughput, and inconsistencies in experimental data. Restraint devices are commonly used for the manipulation of small mammals, and in this manuscript, we describe the construction of two devices that can be used to entrap and restrain G. mellonella larvae prior to injection with pathogenic microbes. These devices reduce the manual handling of larvae and provide an engineering control to protect against accidental needlestick injury while maintaining a high rate of injection. 

Recent advances in on-policy reinforcement learning (RL) methods enabled learning agents in virtual environments to master complex tasks with high-dimensional and continuous observation and action spaces. However, leveraging this family of algorithms in multi-fingered robotic grasping remains a challenge due to large sim-to-real fidelity gaps and the high sample complexity of on-policy RL algorithms. This work aims to bridge these gaps by first reinforcement-learning a multi-fingered robotic grasping policy in simulation that operates in the pixel space of the input: a single depth image. Using a mapping from pixel space to Cartesian space according to the depth map, this method transfers to the real world with high fidelity and introduces a novel attention mechanism that substantially improves grasp success rate in cluttered environments. Finally, the direct-generative nature of this method allows learning of multi-fingered grasps that have flexible end-effector positions, orientations and rotations, as well as all degrees of freedom of the hand. 

Generative Attention Learning (GenerAL) is a framework for high-DOF multi-fingered grasping that is not only robust to dense clutter and novel objects but also effective with a variety of different parallel-jaw and multi-fingered robot hands. This framework introduces a novel attention mechanism that substantially improves the grasp success rate in clutter. Its generative nature allows the learning of full-DOF grasps with flexible end-effector positions and orientations, as well as all finger joint angles of the hand. Trained purely in simulation, this framework skillfully closes the sim-to-real gap. To close the visual sim-to-real gap, this framework uses a single depth image as input. To close the dynamics sim-to-real gap, this framework circumvents continuous motor control with a direct mapping from pixel to Cartesian space inferred from the same depth image. Finally, this framework demonstrates inter-robot generality by achieving over 92% real-world grasp success rates in cluttered scenes with novel objects using two multi-fingered robotic hand-arm systems with different degrees of freedom. 

This work provides an architecture that incorporates depth and tactile information to create rich and accurate 3D models useful for robotic manipulation tasks. This is accomplished through the use of a 3D convolutional neural network (CNN). Offline, the network is provided with both depth and tactile information and trained to predict the object’s geometry, thus filling in regions of occlusion. At runtime, the network is provided a partial view of an object. Tactile information is acquired to augment the captured depth information. The network can then reason about the object’s geometry by utilizing both the collected tactile and depth information. We demonstrate that even small amounts of additional tactile information can be incredibly helpful in reasoning about object geometry. This is particularly true when information from depth alone fails to produce an accurate geometric prediction. Our method is benchmarked against and outperforms other visual-tactile approaches to general geometric reasoning. We also provide experimental results comparing grasping success with our method. 

This work provides a framework for a workspace aware online grasp planner. This framework greatly improves the performance of standard online grasp planning algorithms by incorporating a notion of reachability into the online grasp planning process. Offline, a database of hundreds of thousands of unique end-effector poses were queried for feasibility. At runtime, our grasp planner uses this database to bias the hand towards reachable end-effector configurations. The bias keeps the grasp planner in accessible regions of the planning scene so that the resulting grasps are tailored to the situation at hand. This results in a higher percentage of reachable grasps, a higher percentage of successful grasp executions, and a reduced planning time. We also present experimental results using simulated and real environments. 

Flexible electronic technologies offer the potential for the co-integration of mechanical sensors that measure the state of the flexible surface under actuation or deformation. This format of sensor offers significant opportunities for the instrumentation of existing systems for a range of applications such as touch, measurement of acoustic field, and the detection of deformation modes of a system. Beyond the instrumentation of existing systems, flexible devices can themselves serve as actuators, allowing for sheet-based robotic devices, as well as the development of sensor formats for challenging applications. 

Advancing the sparse regularity method, we prove one‐sided and two‐sided regularity inheritance lemmas for subgraphs of bijumbled graphs, improving on results of Conlon, Fox, and Zhao. These inheritance lemmas also imply improvedH‐counting lemmas for subgraphs of bijumbled graphs, for some H.