The usefulness and versatility of a robotic end-effector depends on the diversity of grasps it can accomplish and also on the complexity of the control methods required to achieve them. We believe that soft hands are able to provide diverse and robust grasping with low control complexity. They possess many mechanical degrees of freedom and are able to implement complex deformations. At the same time, due to the inherent compliance of soft materials, only very few of these mechanical degrees have to be controlled explicitly. Soft hands therefore may combine the best of both worlds. In this paper, we present RBO Hand 2, a highly compliant, underactuated, robust, and dexterous anthropomorphic hand. The hand is inexpensive to manufacture and the morphology can easily be adapted to specific applications. To enable efficient hand design, we derive and evaluate computational models for the mechanical properties of the hand's basic building blocks, called PneuFlex actuators. The versatility of RBO Hand 2 is evaluated by implementing the comprehensive Feix taxonomy of human grasps. The manipulator's capabilities and limits are demonstrated using the Kapandji test and grasping experiments with a variety of objects of varying weight. Furthermore, we demonstrate that the effective dimensionality of grasp postures exceeds the dimensionality of the actuation signals, illustrating that complex grasping behavior can be achieved with relatively simple control.

No abstract

Abstract-The application of deep learning in robotics leads to very specific problems and research questions that are typically not addressed by the computer vision and machine learning communities. In this paper we discuss a number of robotics-specific learning, reasoning, and embodiment challenges for deep learning. We explain the need for better evaluation metrics, highlight the importance and unique challenges for deep robotic learning in simulation, and explore the spectrum between purely data-driven and model-driven approaches. We hope this paper provides a motivating overview of important research directions to overcome the current limitations, and help fulfill the promising potentials of deep learning in robotics.

Abstract-This paper presents a overview of the inaugural Amazon Picking Challenge along with a summary of a survey conducted among the 26 participating teams. The challenge goal was to design an autonomous robot to pick items from a warehouse shelf. This task is currently performed by human workers, and there is hope that robots can someday help increase efficiency and throughput while lowering cost. We report on a 28-question survey posed to the teams to learn about each team's background, mechanism design, perception apparatus, planning and control approach. We identify trends in this data, correlate it with each team's success in the competition, and discuss observations and lessons learned based on survey results and the authors' personal experiences during the challenge.Note to Practitioners: Abstract-Perception, motion planning, grasping, and robotic system engineering has reached a level of maturity that makes it possible to explore automating simple warehouse tasks in semi-structured environments that involve high-mix, low-volume picking applications. This survey summarizes lessons learned from the first Amazon Picking Challenge, highlighting mechanism design, perception, and motion planning algorithms, as well as software engineering practices that were most successful in solving a simplified order fulfillment task. While the choice of mechanism mostly affects execution speed, the competition demonstrated the systems challenges of robotics and illustrated the importance of combining reactive control with deliberative planning.

Disruption Tolerant Networks (DTNs) require routing algorithms that are different from those designed for ad hoc networks. In DTNs, transport of data through the network is achieved through the physical movement of the participants in the network. We address two fundamental problems of routing in DTNs: routing algorithms with robust delivery rates, and management of networks where demand for routes does not match with the movement of peers. For the first problem, we propose the MV algorithm, which is based on observed meetings between peers and visits of peers to geographic locations. We show that our approach can achieve robust delivery rates: 83% of the maximum possible delivery rate, as compared to 64% for fifo buffer management. The advantage remains significant as the offered load of the system is increased an order of magnitude. For the second problem, we propose to augment available routes and capacity in a DTN through autonomous agents (e.g., autonomous blimps or mobile robots). We propose a controller that moves the agent to where network needs are not being met by the movement of peers. Our controller is able to increase delivery between fifteen and twenty-five percent. Our experiments shows that the introduction of even a few agents can dramatically increase the reliability of the message ferrying network. Moreover, our techniques are compatible and offer a robust method of approaching the problems of DTNs.