Keynote Talk Titles and Abstracts
Speaker: Ronald C. Arkin, Mobile Robot Lab, Georgia Tech
Talk Title: Robots that Need to Mislead: Biologically-inspired Machine Deception
Abstract:
Expanding our work in understanding the relationships maintained tin teams of humans and robots, this talk describes previous and ongoing research for the U.S. Navy on deception and its application within robotic systems. Earlier we explored the use of psychological interdependence theory as the basis for producing deception in robotic systems in order to evade capture. More recent work involves studying squirrel hoarding and bird mobbing behavior as it applies to deception, in the first case for misleading a predator, and in the second for feigning strength when none exists. These biological models have been applied to both simulation and robotic systems.
Speaker: Joey Durham, Kiva Systems
Talk Title: Many Robot Systems as the Engine of Ecommerce
Abstract:
Kiva’s mobile fulfillment system blends techniques from AI, Controls Systems, Machine Learning, Operations Research and other engineering disciplines into the world’s largest mobile robotic platform. Kiva uses hundreds to thousands of mobile robots to carry inventory shelves around distribution centers for Amazon, Staples, The Gap, and many others. Kiva currently has equipment in over 30 warehouses in four countries. This talk will describe the business case for mobile robotic fulfillment and also some of the technical keys which enabled Kiva to successfully cross the reality gap.
Speaker: Jorge Soares, EPFL
Talk Title: Multi-robot marine systems: development and deployment
Abstract:
Research in autonomous marine vehicles has been steadily increasing, and the trend is expected to continue as we move to using robots to execute previously human-performed tasks in extreme undersea environments. Nevertheless, working in the marine and, especially, the underwater domain also present unique challenges to robotics: communication and localization are limited, deployments are costly and time-consuming, and the environment is generally not too inviting for either robots or humans. In this talk, we will go over these and other challenges, using the ongoing development process of our vehicle and a range-based formation algorithm as a case study.
Speaker: Edwin Olson, APRIL Lab, University of Michigan
Talk Title: Humans and Multi-Robot Systems
Abstract:
How do we build autonomous multi-robot systems that are capable of operating in complex/unstructured environments? In these hard cases, it is difficult to make even a single robot work, much less a large team. We argue that having humans in the loop is critical to achieving useful levels of reliability, but that this creates new challenges relating to situational awareness, cognitive loading, and user interfaces. We describe our work in these areas, and describe how our autonomy approaches support better user experiences.
Speaker: Matthew Turpin, GRASP Lab, University of Pennsylvania
Abstract:
Large teams of robots have been implemented to great success in Kiva's automated warehouses as well as UPenn's and ETH's swarms of quadrotors. In settings such as these, robots must plan paths which avoid collisions with other robots and obstacles in the environment. Unfortunately, trajectory planning for large teams of robots generally suffers from either the curse of dimensionality or lack of completeness. I will demonstrate that relaxing the assumption of labeling each robot and specifying a fixed assignment of robots to destinations in the trajectory generation problem yields a number of computational and performance benefits. My algorithm to solve this Concurrent Assignment and Planning of Trajectories (CAPT) problem has bounded computational complexity of O(N^3), preserves completeness properties of a user specified single agent motion planner, and tends to minimize effort exerted by any one robot. This algorithm generates solutions to variants of the CAPT problem in settings ranging from kinematic robots in an obstacle free environment to teams of robots with 4th order dynamics in a cluttered environment. Finally, I will show experimental results of the algorithm applied on teams of second order aquatic vehicles as well as on quadrotor micro aerial vehicles. I will also outline how time consuming aspects of this approach can be parallelized and discuss possible decentralized implementations.
Speaker: Lorenzo Sabattini, U of Modena & Reggio Emilia
Talk Title: Multi-AGV systems for factory logistics
Abstract:
Nowadays, product processing and packaging have often reached a high degree of automation, in which energy consumption awareness, agile manufacturing and product customization are well addressed. Factory logistics plays an important role affecting production efficiency and energy consumption. In fact, it takes care of moving raw materials and final products among the production lines, the factory warehouse, and the shipment department. Therefore, any bottleneck and inefficiency in factory logistics decreases the productivity level of the whole factory.
It would be desirable to consider and optimize the entire manufacturing process in a holistic way, including factory logistics as well. Automation and optimization should be applied to the full manufacturing chain in order to increase the efficiency and the flexibility of the entire process, while ensuring safe operation and decreasing energy consumption.
Large scale employment of systems of multiple AGVs would greatly improve the automation of factory logistics. The purpose of this talk is to highlight the main characteristics of currently employed multi-AGV systems, specifically in terms of flexibility, safety, and interaction with human operators. A technological roadmap will be sketched to promote wider application of AGV systems in factory logistics.
Speaker: Giuseppe Casalino, University of Genova
Talk Title: Control and Coordination of Underwater Intervention Robotic Systems
Abstract:
The presentation formerly summarizes the results very recently achieved in the field of control and coordination of underwater intervention robotic systems, with special focus on underwater floating manipulators; for which a unifying algorithmic control structure has been devised; possibly representing the key toward much more challenging operative extensions; even of cooperative type among different floating and non-floating mobile manipulator agents. These challenges are then better outlined as the topics for future research activities. Then, on their basis a general vision for much more extended applicative scenarios is proposed.