Michael Laskey

Learn More
Belief space planning provides a principled framework to compute motion plans that explicitly gather information from sensing, as necessary, to reduce uncertainty about the robot and the environment. We consider the problem of planning in Gaussian belief spaces, which are parameterized in terms of mean states and covariances describing the uncertainty. In(More)
This paper presents the Dexterity Network (Dex-Net) 1.0, a dataset of 3D object models and a sampling-based planning algorithm to explore how Cloud Robotics can be used for robust grasp planning. The algorithm uses a Multi- Armed Bandit model with correlated rewards to leverage prior grasps and 3D object models in a growing dataset that currently includes(More)
To reduce data collection time for deep learning of robust robotic grasp plans, we explore training from a synthetic dataset of 6.7 million point clouds, grasps, and robust analytic grasp metrics generated from thousands of 3D models from DexNet 1.0 in randomized poses on a table. We use the resulting dataset, Dex-Net 2.0, to train a Grasp Quality(More)
Exercise has important effects on skeletal mineralization. Changes in bone mineral density (BMD) and bone mineral content (BMC) as measured by dual energy X-ray absorptiometry were investigated in a group of 17 male novice college oarsmen over a 7-month period and were compared with eight age-matched controls. The rowing training programme consisted of(More)
The acute procedural outcome of percutaneous transluminal coronary angioplasty in 304 patients with unstable angina was retrospectively examined with respect to the influence of prolonged preprocedural intravenous heparin therapy. Clinical and angiographic success in 135 patients receiving heparin therapy for greater than or equal to 24 hours was 91% while(More)
Precise control of industrial automation systems with non-linear kinematics due to joint elasticity, variation in cable tensioning, or backlash is challenging; especially in systems that can only be controlled through an interface with an imprecise internal kinematic model. Cable-driven Robotic Surgical Assistants (RSAs) are one example of such an(More)
For applications such as Amazon warehouse order fulfillment, robots must grasp a desired object amid clutter: other objects that block direct access. This can be difficult to program explicitly due to uncertainty in friction and push mechanics and the variety of objects that can be encountered. Deep Learning networks combined with Online Learning from(More)
Motivated by recent advances in Deep Learning for robot control, this paper considers two learning algorithms in terms of how they acquire demonstrations from fallible human supervisors. Human-Centric (HC) sampling is a standard supervised learning algorithm, where a human supervisor demonstrates the task by teleoperating the robot to provide trajectories(More)
Online learning from demonstration algorithms such as DAgger can learn policies for problems where the system dynamics and the cost function are unknown. However they impose a burden on supervisors to respond to queries each time the robot encounters new states while executing its current best policy. The MMD-IL algorithm reduces supervisor burden by(More)
For applications such as warehouse order fulfillment, robot grasps must be robust to uncertainty arising from sensing, mechanics, and control. One way to achieve robustness is to evaluate the performance of candidate grasps by sampling perturbations in shape, pose, and gripper approach and to compute the probability of force closure for each candidate to(More)