TechTalks.Tv beta

For several applications like surveillance, search and rescue in dis- aster regions, and exploration, the use of a single or a of group of mobile robots is getting more and more common. Nevertheless, when the tasks become extremely complex and high-level cognitive-based decisions are required online (as, e.g., during exploration of very clut- tered, dynamic and unpredictable environments for search and rescue applications), complete autonomy is still far from being reached and humans intervention/assistance is necessary. In this context, haptic teleoperation systems, where a human operator commands a remote robot through a local interface and receive an informative haptic feed- back, allow to exploit humans intelligence to solve tasks too complex for nowadays robots. This full day workshop will focus on the haptic teleoperation of a single or a team of mobile robots. Its main goal is to present recent results in the eld and to establish a discussion on the technological, mathematical and psychophysical aspects of this problem.

The SDIR workshop series is a forum where researchers and prac- titioners share best practices, identify strategic research directions, and plan joint initiatives in robot software development. The specic topic of this workshop is \Programming Languages in Robotics." The full-day workshop is structured in three sessions.

1. Presentation Session: (morning) will include a keynote presen- tation by an invited expert and a set of talks that represent a selected set of accepted papers.
2. Poster Session: (afternoon one hour) will give the opportunity for all authors of accepted papers to discuss/demonstrate their work.
3. Group Discussion Session: (afternoon) will be organized as a working group session that maximizes participation from indi- viduals: we will start o with an initial list of questions followed by a solicitation from participants. Then, the organizers will break up the group into splinter groups that will discuss each of the questions and report back to the larger group.

Signicant advances in software development environments and cost reductions of vehicle and sensor platforms have resulted in tremen- dous growth of R&D for many-robot systems and distributed sensor networks worldwide. These eorts have yielded a plethora of theo- retical results and online videos of many-robot systems achieving re- markable feats, but few of these systems are nding their way into the real world beyond prototype demonstrations. This full-day work- shop will bring together experts in many-robot systems (including multi-robot teams, swarms, mobile sensor and communication net- works, other networked mobile robots) to investigate the gap between theory (including research prototyping and demonstrations) and real world applications of many-robot systems. We will seek to identify killer apps along with key technical issues hampering the deployment of many robot systems, and discuss solutions towards moving these systems out of the laboratories and into real-world application envi- ronments. We refer to this process as \Crossing the Reality Gap". We solicit submissions of extended abstracts from researchers working on crossing the reality gap for many-robot systems. The workshop will feature a combination of invited talks, oral and poster presentations, and a panel discussion on the topic \What government organizations need from researchers to transition many-robot systems to operational use.

Following the rst successful workshop at the 2011 ICRA, we would like to extend the Bio-Bots workshop for the 2012 ICRA with a re- newed scope. Our shared view in this workshop is that breakthroughs in bio-articial muscles, biosensors, and synthetic biology are pro- viding components usable for building biological robots. Bacteria- propelled micro-nano robots have already been built, having signi- cant impacts upon medicine and biology. Technologies for culturing cells and tissues to produce novel sensors, actuators, and processors have also been developed, which can be integrated into micro-nano robots for advanced applications. The boundary between biology and robotics is being fused in this emerging eld. The objective of this workshop is to display the state-of-the-art of Bio-Bots, discuss key technologies and challenges, and address system-level issues, applica- tions, and opportunities. We will also address educational issues: how we can best educate students who will work in the eld where en- gineering and biology are seamlessly integrated. Nine speakers from the robotics community have already been conrmed. A few more speakers from synthetic biology and tissue engineering will be invited to promote cross-disciplinary communications.

In emerging robotic applications, in which robots need to coop- erate closely with humans, traditional rigid structures and sti ac- tuation systems should be properly modeled and controlled in order to achieve adaptability, compliancy and safety. An alternative design approach is to build actuators with physically adjustable compliance and damping, able to store and release mechanical energy, to react softly when touching the environment, and intrinsically safe, just like human muscles do. Robots and biomechatronic systems can be given similar capabilities as humans by implementing variable impedance actuators, characterized by the property that their apparent output stiness, and thus the stiness of the actuated joint, can be changed independently from the actuator output position. Variable impedance actuators realize robust, energy-ecient and highly dynamic systems, which permit the embodiment of natural characteristics, found in bi- ological systems, and implementable into a new generation of robots. This full-day workshop covers the challenges related to the technolog- ical realization and the functionalities of such actuation systems, in terms of both mechanical design and control, by mostly focusing on complex robotic and biomechatronic applications, such as robotic ma- nipulation, bipedal and multi-legged locomotion, prosthetics (hands, arms and legs), rehabilitation devices and social robots (humanoids).

This all-day tutorial introduces the audience to reinforcement learning. Prior experience in this area is not assumed. In the first half of this tutorial we will cover the foundations of reinforcement learning: Markov decision processes, value iteration, policy iteration, linear programming for solving an MDP, function approximation, model-free versus model-based learning, Q-learning, TD-learning, policy search, the likelihood ratio policy gradient, the policy gradient theorem, actor-critic, natural gradient and importance sampling. In the second half of this tutorial we will discuss example success stories and open problems.

Point clouds are one of the most fascinating and challenging sensor streams, leading to countless publications. The advent of low cost 3D cameras, such as the Microsoft Kinect, has led to a wide range of new ideas and projects in this field. The PCL community tries to bring together all these activities to produce one open source library. Backed up by leading institutions and researchers around the world, as well as dedicated senior level programmers, this gives us the opportunity to join all the loose ends in point cloud processing. The point cloud library gives every researcher the opportunity to try new ideas fast as well as discuss them with and get support from a big community. Most of this is done through electronic communication, including mailing lists and chat systems, but to share it with the broader robotics community, as well as to get more people involved, we propose a one day tutorial. We will give an introduction to the library, guide the attendees in their first steps using it, as well as show what great results have been achieved with it already. PCL is a truly open community with a low administrative structure. We have especially designed our documentation to guide new users and have created help channels to give them the opportunity to rapidly become contributors.

This all-day tutorial introduces the audience to motion planning algorithms and associated mathematical concepts. Prior experience in this area is not assumed. The morning part starts from the basics of collision-free path planning by introducing geometric representations, transformations, configuration spaces, sampling-based motion planning, and combinatorial motion planning. The afternoon part covers methods that address many concerns which arise in practice when the robot's environment is changing or is incompletely specified. This falls under the heading of planning in dynamic environments. Fundamental limitations of planning in this context are discussed, followed by a survey of several successful approaches from specific contexts, such as planning for humanoids, autonomous vehicles, and virtual agents.

IPDPS is an international forum for engineers and scientists from around the world to present their latest research findings in all aspects of parallel computation. In addition to technical sessions of submitted paper presentations, the meeting offers workshops, tutorials, and commercial presentations & exhibits. IPDPS represents a unique international gathering of computer scientists from around the world. Now, more than ever, we prize this annual meeting as a testament to the strength of international cooperation in seeking to apply computer science technology to the betterment of our global village.

IEEE Computer Vision and Pattern Recognition. June 16-19 2012.