We introduce CHAMP, an algorithm for online Bayesian changepoint detection in settings where it is difficult or undesirable to integrate over the parameters of candidate models. CHAMP is used in combination with sever...
详细信息
We introduce CHAMP, an algorithm for online Bayesian changepoint detection in settings where it is difficult or undesirable to integrate over the parameters of candidate models. CHAMP is used in combination with several articulation models to detect changes in articulated motion of objects in the world, allowing a robot to infer physically-grounded task information. We focus on three settings where a changepoint model is appropriate: objects with intrinsic articulation relationships that can change over time, object-object contact that results in quasi-static articulated motion, and assembly tasks where each step changes articulation relationships. We experimentally demonstrate that this system can be used to infer various types of information from demonstration data including causal manipulation models, human-robot grasp correspondences, and skill verification tests.
The Symposium on "New Frontiers in Human-Robot Interaction (HRI)" is the fourth of a series of symposia held in conjunction with the AISB convention. Its topics cover cutting-edge interdisciplinary research ...
详细信息
The Symposium on "New Frontiers in Human-Robot Interaction (HRI)" is the fourth of a series of symposia held in conjunction with the AISB convention. Its topics cover cutting-edge interdisciplinary research on understanding, designing, and evaluating robotic systems for and with humans. Its main difference to other HRI-related conferences and workshops is its inclusiveness for exploratory research and the amount of time for open discussion. This year's symposium consists of six sessions covering topics such as verbal and non-verbal interaction, people's perception of robots, and ethical issues. Moreover, it includes keynote talks by Mark Coeckelbergh and Angelika Peer and a panel on the topic "Robot Perception and Acceptance".
In this paper, a hierarchical learning algorithm is developed for classifying large-scale patient records, e.g., categorizing large-scale patient records into large numbers of known patient categories (i.e., thousands...
详细信息
Robots are being designed to provide companionship, but there is some concern that they could lead to a reduction in human contact for vulnerable populations. However, some field data suggests that robots may have a s...
详细信息
Robots are being designed to provide companionship, but there is some concern that they could lead to a reduction in human contact for vulnerable populations. However, some field data suggests that robots may have a social mediation effect in humanhuman interactions. This study examined social mediation effects in a controlled laboratory setting. In this study 114 unacquainted female volunteers were put in pairs and randomised to interact together with an active Paro, an inactive Paro, or a dinosaur toy robot. Each pair was invited to evaluate and interact with the robot together during a ten minute session. Post-interaction questionnaires measured the quality of dyadic interaction between participants during the session. Our results indicate that the strongest social mediation effect was from the active Paro.
We introduce a particle filter-based approach to representing and actively reducing uncertainty over articulated motion models. The presented method provides a probabilistic model that integrates visual observations w...
详细信息
We introduce a particle filter-based approach to representing and actively reducing uncertainty over articulated motion models. The presented method provides a probabilistic model that integrates visual observations with feedback from manipulation actions to best characterize a distribution of possible articulation models. We evaluate several action selection methods to efficiently reduce the uncertainty about the articulation model. The full system is experimentally evaluated using a PR2 mobile manipulator. Our experiments demonstrate that the proposed system allows for intelligent reasoning about sparse, noisy data in a number of common manipulation scenarios.
When large-scale online geo-tagged images come into view, it is important to leverage geographic information for web image retrieval. In this paper, a geo-metadata based image retrieval system is proposed using both t...
详细信息
Electroencephalography is a commonly used tool for presurgical evaluation of epilepsy patients. In this paper, we present a quantitative evaluation of interictal high frequency oscillations (HFOs) in scalp Electroence...
详细信息
In this paper, the control problem is addressed for a hybrid PDE-ODE system that describes a nonuniform gantry crane system with constrained tension. A bottom payload hangs from the top gantry by connecting a flexible...
详细信息
ISBN:
(纸本)9781479947249
In this paper, the control problem is addressed for a hybrid PDE-ODE system that describes a nonuniform gantry crane system with constrained tension. A bottom payload hangs from the top gantry by connecting a flexible cable. The flexible cable is nonuniform due to the spatiotemporally varying tension applied to the system. Cooperative control laws are proposed and the Integral-Barrier Lyapunov Functions are employed for stability analysis of the closed-loop system. Adaption laws are developed for handling parametric uncertainties. The bounded stability is guaranteed through rigorous analysis without any simplification of the dynamics. In the end, numerical simulations are displayed to illustrate the performance of the proposed cooperative control.
暂无评论