Jonathan Lee

Robot grasping in clutter: Using a hierarchy of supervisors for learning from demonstrations

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 Demonstration (LfD) algorithms such as DAgger and SHIV have potential to learn robot control policies for such tasks where the input is a camera image and system dynamics and the cost function are unknown. To explore this idea, we introduce a version of the grasping in clutter problem where a yellow cylinder must be grasped by a planar robot arm amid extruded objects in a variety of shapes and positions. To reduce the burden on human experts to provide demonstrations, we propose using a hierarchy of three levels of supervisors: a fast motion planner that ignores obstacles, crowd-sourced human workers who provide appropriate robot control values remotely via online videos, and a local human expert. Physical experiments suggest that with 160 expert demonstrations, using the hierarchy of supervisors can increase the probability of a successful grasp (reliability) from 55% to 90%.

Comparing human-centric and robot-centric sampling for robot deep learning from demonstrations

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 consisting of state-control pairs. Robot-Centric (RC) sampling is an increasingly popular alternative used in algorithms such as DAgger, where a human supervisor observes the robot execute a learned policy and provides corrective control labels for each state visited. We suggest RC sampling can be challenging for human supervisors and prone to mislabeling. RC sampling can also induce error in policy performance because it repeatedly visits areas of the state space that are harder to learn. Although policies learned with RC sampling can be superior to HC sampling for standard learning models such as linear SVMs, policies learned with HC sampling may be comparable to RC when applied to expressive learning models such as deep learning and hyper-parametric decision trees, which can achieve very low training error provided there is enough data. We compare HC and RC using a grid world environment and a physical robot singulation task. In the latter the input is a binary image of objects on a planar worksurface and the policy generates a motion in the gripper to separate one object from the rest. We observe in simulation that for linear SVMs, policies learned with RC outperformed those learned with HC but that using deep models this advantage disappears. We also find that with RC, the corrective control labels provided by humans can be highly inconsistent. We prove there exists a class of examples in which at the limit, HC is guaranteed to converge to an optimal policy while RC may fail to converge. These results suggest a form of HC sampling may be preferable for highly-expressive learning models and human supervisors.

Automatic Fault Location on Distribution Networks Using Synchronized Voltage Phasor Measurement Units

Automatic fault location on the distribution system is a necessity for a resilient grid with fast service restoration after an outage. Motivated by the development of low cost synchronized voltage phasor measurement units (PMUs) for the distribution system, this paper describes how PMU data during a fault event can be used to accurately locate faults on the primary distribution system. Rather than requiring many specialized line sensors to enable fault location, the proposed approach leverages a PMU data stream that can be used for a variety of applications, making it easier to justify the investment in fault location. The accuracy of existing automatic fault location techniques are dependent either on dense deployments of line sensors or unrealistically accurate models of system loads. This paper demonstrates how synchronized voltage measurements enable sufficiently accurate fault location with relatively few instrumentation devices and relatively low fidelity system models. The IEEE 123 bus distribution feeder is examined as a test case, and the proposed algorithm is demonstrated to be robust to variations in total load and uncertainty in the response of loads to voltage sags during a sample set of varied fault conditions.Copyright