Technical session talks from ICRA 2012
TechTalks from event: Technical session talks from ICRA 2012
Conference registration code to access these videos can be accessed by visiting this link: PaperPlaza. Step-by-step to access these videos are here: step-by-step process .
Why some of the videos are missing? If you had provided your consent form for your video to be published and still it is missing, please contact firstname.lastname@example.org
Learning and Adaptation Control of Robotic Systems II
Online Learning of Varying Stiffness through Physical Human-Robot InteractionProgramming by Demonstration offers an intuitive framework for teaching robots how to perform various tasks without having to preprogram them. It also offers an intuitive way to provide corrections and refine teaching during task execution. Previously, mostly position constraints have been taken into account when teaching tasks from demonstrations. In this work, we tackle the problem of teaching tasks that require or can benefit from varying stiffness. This extension is not trivial, as the teacher needs to have a way of communicating to the robot what stiffness it should use. We propose a method by which the teacher can modulate the stiffness of the robot in any direction through physical interaction. The system is incremental and works online, so that the teacher can instantly feel how the robot learns from the interaction. We validate the proposed approach on two experiments on a 7-Dof Barrett WAM arm.
Reinforcement Planning: RL for Optimal PlannersSearch based planners such as A* and Dijkstraâ€™s algorithm are proven methods for guiding todayâ€™s robotic systems. Although such planners are typically based upon a coarse approximation of reality, they are nonetheless valuable due to their ability to reason about the future, and to generalize to previously unseen scenarios. However, encoding the desired behavior of a system into the underlying cost function used by the planner can be a tedious and error-prone task. We introduce Reinforcement Planning, which extends gradient based reinforcement learning algorithms to automatically learn useful surrogate cost functions for optimal planners. Reinforcement Planning presents several advantages over other learning approaches to planning in that it is not limited by the expertise of a human demonstrator, and that it acknowledges the domain of the planner is a simplified model of the world. We demonstrate the effectiveness of our method in learning to solve a noisy physical simulation of the well-known â€œmarble mazeâ€ toy.
Adaptive Collaborative Estimation of Multi-Agent Mobile Robotic SystemsCollaborative multi-robot systems are used in a vast array of fields for their innate ability to parallelize domain problems for faster execution. These systems are generally comprised of multiple identical robotic systems in order to simplify manufacturability and programmability, reduce cost, and provide fault tolerance. This work takes advantage of the homogeneity and multiplicity of multi-robot systems to enhance the convergence rate of adaptive dynamic parameter estimation through collaboration. The collaborative adaptive dynamic parameter estimation of multi-robot systems is accomplished by penalizing the pair-wise disagreement of both state and parameter estimates. Consensus and convergence is based on Lyapunov stability arguments. Simulation studies with multiple Pioneer 3-DX systems provides verification of the proposed theoretic collaborative adaptive parameter estimation predictions.
Lingodroids: Learning Terms for TimeFor humans and robots to communicate using natural language it is necessary for the robots to develop concepts and associated terms that correspond to the human use of words. Time and space are foundational concepts in human language, and to develop a set of words that correspond to human notions of time and space, it is necessary to take into account the way that they are used in natural human conversations, where terms and phrases such as â€˜soonâ€™, â€˜in a whileâ€™, or â€˜nearâ€™ are often used. We present language learning robots called Lingodroids that can learn and use simple terms for time and space. In previous work, the Lingodroids were able to learn terms for space. In this work we extend their abilities by adding temporal variables which allow them to learn terms for time. The robots build their own maps of the world and interact socially to form a shared lexicon for location and duration terms. The robots successfully use the shared lexicons to communicate places and times to meet again.
Teaching Nullspace Constraints in Physical Human-Robot Interaction Using Reservoir ComputingA major goal of current robotics research is to enable robots to become co-workers that collaborate with humans efficiently and adapt to changing environments or workflows. We present an approach utilizing the physical interaction capabilities of compliant robots with data-driven and model-free learning in a coherent system in order to make fast reconfiguration of redundant robots feasible. Users with no particular robotics knowledge can perform this task in physical interaction with the compliant robot, for example to reconfigure a work cell due to changes in the environment. For fast and efficient training of the respective mapping, an associative reservoir neural network is employed. It is embedded in the motion controller of the system, hence allowing for execution of arbitrary motions in task space. We describe the training, exploration and the control architecture of the systems as well as present an evaluation on the KUKA Light-Weight Robot. Our results show that the learned model solves the redundancy resolution problem under the given constraints with sufficient accuracy and generalizes to generate valid joint-space trajectories even in untrained areas of the workspace.
A Bayesian Nonparametric Approach to Modeling Battery HealthThe batteries of many consumer products are often both a substantial portion of the item's cost and commonly a first point of failure. Accurately predicting remaining battery life can lower costs by reducing unnecessary battery replacements. Unfortunately, battery dynamics are extremely complex, and we often lack the domain knowledge required to construct a model by hand. In this work, we take a data-driven approach and aim to learn a model of battery time-to-death from training data. Using a Dirichlet process prior over mixture weights, we learn an infinite mixture model for battery health. The Bayesian aspect of our model helps to avoid over-fitting while the nonparametric nature of the model allows the data to control the size of the model, preventing under-fitting. We demonstrate our model's effectiveness by making time-to-death predictions using real data from iRobot Roomba batteries.