There has been significant recent work on data-driven algorithms for learning general-purpose grasping policies. However, these policies can consis- tently fail to grasp challenging objects which are significantly out of the distribution of objects in the training data or which have very few high quality grasps. Moti- vated by such objects, we propose a novel problem setting, Exploratory Grasping, for efficiently discovering reliable grasps on an unknown polyhedral object via sequential grasping, releasing, and toppling. We formalize Exploratory Grasping as a Markov Decision Process where we assume that the robot can (1) distinguish stable poses of a polyhedral object of unknown geometry, (2) generate grasp can- didates on these poses and execute them, (3) determine whether each grasp is successful, and (4) release the object into a random new pose after a grasp success or topple the object after a grasp failure. We study the theoretical complexity of Exploratory Grasping in the context of reinforcement learning and present an efficient bandit-style algorithm, Bandits for Online Rapid Grasp Exploration Strategy (BORGES), which leverages the structure of the problem to efficiently discover high performing grasps for each object stable pose. BORGES can be used to complement any general-purpose grasping algorithm with any grasp modality (parallel-jaw, suction, multi-fingered, etc) to learn policies for objects in which they exhibit persistent failures. Simulation experiments suggest that BORGES can significantly outperform both general-purpose grasping pipelines and two other online learning algorithms and achieves performance within 5% of the optimal policy within 1000 and 8000 timesteps on average across 46 challenging objects from the Dex-Net adversarial and EGAD! object datasets, respectively. Initial physical experiments suggest that BORGES can improve grasp success rate by 45% over a Dex-Net baseline with just 200 grasp attempts in the real world. See https://tinyurl.com/exp-grasping for supplementary material and videos.
more »
« less
Self-Reflective Learning Strategy for Persistent Autonomy of Aerial Manipulators
Autonomous aerial manipulators have great potentials to assist humans or even fully automate manual labor-intensive tasks such as aerial cleaning, aerial transportation, infrastructure repair, and agricultural inspection and sampling. Reinforcement learning holds the promise of enabling persistent autonomy of aerial manipulators because it can adapt to different situations by automatically learning optimal policies from the interactions between the aerial manipulator and environments. However, the learning process itself could experience failures that can practically endanger the safety of aerial manipulators and hence hinder persistent autonomy. In order to solve this problem, we propose for the aerial manipulator a self-reflective learning strategy that can smartly and safely finding optimal policies for different new situations. This self-reflective manner consists of three steps: identifying the appearance of new situations, re-seeking the optimal policy with reinforcement learning, and evaluating the termination of self-reflection. Numerical simulations demonstrate, compared with conventional learning-based autonomy, our strategy can significantly reduce failures while still can finish the given task.
more » « less- Award ID(s):
- 1652454
- NSF-PAR ID:
- 10154805
- Date Published:
- Journal Name:
- ASME 2019 Dynamic Systems and Control Conference
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
To facilitate sensing and physical interaction in remote and/or constrained environments, high-extension, lightweight robot manipulators are easier to transport and reach substantially further than traditional serial chain manipulators. We propose a novel planar 3-degree-of-freedom manipulator that achieves low weight and high extension through the use of a pair of spooling bistable tapes, commonly used in self-retracting tape measures, which are pinched together to form a reconfigurable revolute joint. The pinching action flattens the tapes to produce a localized bending region, resulting in a revolute joint that can change its orientation by cable tension and its location on the tapes though friction-driven movement of the pinching mechanism. We present the design, implementation, kinematic modeling, stiffness behavior of the revolute joint, and quasi-static performance of this manipulator. In particular, we demonstrate the ability of the manipulator to reach specified targets in free space, reach a 2D target with various orientations, and maintain an end-effector angle or stationary bending point while changing the other. The long-term goal of this work is to integrate the manipulator with an aerial robot to enable more capable aerial manipulation.more » « less
-
Autonomous Mobility-on-Demand (AMoD) systems represent an attractive alternative to existing transportation paradigms, currently challenged by urbanization and increasing travel needs. By centrally controlling a fleet of self-driving vehicles, these systems provide mobility service to customers and are currently starting to be deployed in a number of cities around the world. Current learning-based approaches for controlling AMoD systems are limited to the single-city scenario, whereby the service operator is allowed to take an unlimited amount of operational decisions within the same transportation system. However, real-world system operators can hardly afford to fully re-train AMoD controllers for every city they operate in, as this could result in a high number of poor-quality decisions during training, making the single-city strategy a potentially impractical solution. To address these limitations, we propose to formalize the multi-city AMoD problem through the lens of meta-reinforcement learning (meta-RL) and devise an actor-critic algorithm based on recurrent graph neural networks. In our approach, AMoD controllers are explicitly trained such that a small amount of experience within a new city will produce good system performance. Empirically, we show how control policies learned through meta-RL are able to achieve near-optimal performance on unseen cities by learning rapidly adaptable policies, thus making them more robust not only to novel environments, but also to distribution shifts common in real-world operations, such as special events, unexpected congestion, and dynamic pricing schemes.more » « less
-
more » « less
ABSTRACT Introduction Remote military operations require rapid response times for effective relief and critical care. Yet, the military theater is under austere conditions, so communication links are unreliable and subject to physical and virtual attacks and degradation at unpredictable times. Immediate medical care at these austere locations requires semi-autonomous teleoperated systems, which enable the completion of medical procedures even under interrupted networks while isolating the medics from the dangers of the battlefield. However, to achieve autonomy for complex surgical and critical care procedures, robots require extensive programming or massive libraries of surgical skill demonstrations to learn effective policies using machine learning algorithms. Although such datasets are achievable for simple tasks, providing a large number of demonstrations for surgical maneuvers is not practical. This article presents a method for learning from demonstration, combining knowledge from demonstrations to eliminate reward shaping in reinforcement learning (RL). In addition to reducing the data required for training, the self-supervised nature of RL, in conjunction with expert knowledge-driven rewards, produces more generalizable policies tolerant to dynamic environment changes. A multimodal representation for interaction enables learning complex contact-rich surgical maneuvers. The effectiveness of the approach is shown using the cricothyroidotomy task, as it is a standard procedure seen in critical care to open the airway. In addition, we also provide a method for segmenting the teleoperator’s demonstration into subtasks and classifying the subtasks using sequence modeling.
Materials and Methods A database of demonstrations for the cricothyroidotomy task was collected, comprising six fundamental maneuvers referred to as surgemes. The dataset was collected by teleoperating a collaborative robotic platform—SuperBaxter, with modified surgical grippers. Then, two learning models are developed for processing the dataset—one for automatic segmentation of the task demonstrations into a sequence of surgemes and the second for classifying each segment into labeled surgemes. Finally, a multimodal off-policy RL with rewards learned from demonstrations was developed to learn the surgeme execution from these demonstrations.
Results The task segmentation model has an accuracy of 98.2%. The surgeme classification model using the proposed interaction features achieved a classification accuracy of 96.25% averaged across all surgemes compared to 87.08% without these features and 85.4% using a support vector machine classifier. Finally, the robot execution achieved a task success rate of 93.5% compared to baselines of behavioral cloning (78.3%) and a twin-delayed deep deterministic policy gradient with shaped rewards (82.6%).
Conclusions Results indicate that the proposed interaction features for the segmentation and classification of surgical tasks improve classification accuracy. The proposed method for learning surgemes from demonstrations exceeds popular methods for skill learning. The effectiveness of the proposed approach demonstrates the potential for future remote telemedicine on battlefields.
-
In this report, we present the system design, operational strategy, and results of coordinated multivehicle field demonstrations of autonomous marine robotic technologies in search-for-life missions within the Pacific shelf margin of Costa Rica and the Santorini-Kolumbo caldera complex, which serve as analogs to environments that may exist in oceans beyond Earth. This report focuses on the automation of remotely operated vehicle (ROV) manipulator operations for targeted biological sample-collection-and-return from the seafloor. In the context of future extraterrestrial exploration missions to ocean worlds, an ROV is an analog to a planetary lander, which must be capable of high-level autonomy. Our field trials involve two underwater vehicles, the SuBastian ROV and the Nereid Under Ice (NUI) hybrid ROV for mixed initiative (i.e., teleoperated or autonomous) missions, both equipped seven-degrees-of-freedom hydraulic manipulators. We describe an adaptable, hardware-independent computer vision architecture that enables high-level automated manipulation. The vision system provides a three-dimensional understanding of the workspace to inform manipulator motion planning in complex unstructured environments. We demonstrate the effectiveness of the vision system and control framework through field trials in increasingly challenging environments, including the automated collection and return of biological samples from within the active undersea volcano Kolumbo. Based on our experiences in the field, we discuss the performance of our system and identify promising directions for future research.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1115/DSCC2019-9086
