Conference
International Symposium on Experimental Robotics
About: International Symposium on Experimental Robotics is an academic conference. The conference publishes majorly in the area(s): Robot & Mobile robot. Over the lifetime, 1053 publications have been published by the conference receiving 23103 citations.
Topics: Robot, Mobile robot, Robot control, Robotics, Control theory
Papers published on a yearly basis
Papers
More filters
••
01 Jan 2014TL;DR: This paper presents RGB-D Mapping, a full 3D mapping system that utilizes a novel joint optimization algorithm combining visual features and shape-based alignment to achieve globally consistent maps.
Abstract: RGB-D cameras are novel sensing systems that capture RGB images along with per-pixel depth information. In this paper we investigate how such cameras can be used in the context of robotics, specifically for building dense 3D maps of indoor environments. Such maps have applications in robot navigation, manipulation, semantic mapping, and telepresence. We present RGB-D Mapping, a full 3D mapping system that utilizes a novel joint optimization algorithm combining visual features and shape-based alignment. Visual and depth information are also combined for view-based loop closure detection, followed by pose optimization to achieve globally consistent maps.We evaluate RGB-D Mapping on two large indoor environments, and show that it effectively combines the visual and shape information available from RGB-D cameras.
971 citations
••
01 Jan 2006TL;DR: A successful application of reinforcement learning to designing a controller for sustained inverted flight on an autonomous helicopter, using a stochastic, nonlinear model of the helicopter’s dynamics.
Abstract: Helicopters have highly stochastic, nonlinear, dynamics, and autonomous helicopter flight is widely regarded to be a challenging control problem. As helicopters are highly unstable at low speeds, it is particularly difficult to design controllers for low speed aerobatic maneuvers. In this paper, we describe a successful application of reinforcement learning to designing a controller for sustained inverted flight on an autonomous helicopter. Using data collected from the helicopter in flight, we began by learning a stochastic, nonlinear model of the helicopter’s dynamics. Then, a reinforcement learning algorithm was applied to automatically learn a controller for autonomous inverted hovering. Finally, the resulting controller was successfully tested on our autonomous helicopter platform.
587 citations
••
28 Oct 1993TL;DR: The interaction of an autonomous mobile robot with the real world critically depends on the robots morphology and on its environment Building a model of these aspects is extremely complex, making simulation insufficient for accurate validation of control algorithms as mentioned in this paper.
Abstract: The interaction of an autonomous mobile robot with the real world critically depends on the robots morphology and on its environment Building a model of these aspects is extremely complex, making simulation insufficient for accurate validation of control algorithms
446 citations
•
01 Jan 2004
TL;DR: The design and experimental validation of a nonholonomic model for steering flexible needles with bevel tips are considered, which generalizes the standard three degree-of-freedom (DOF) non holonomic unicycle and bicycle models to 6 DOF using Lie group theory.
Abstract: As a flexible needle with a bevel tip is pushed through soft tissue, the asymmetry of the tip causes the needle to bend. We propose that, by using nonholonomic kinematics, control, and path planning, an appropriately designed needle can be steered through tissue to reach a specified 3D target. Such steering capability could enhance targeting accuracy and may improve outcomes for percutaneous therapies, facilitate research on therapy effectiveness, and eventually enable new minimally invasive techniques. In this paper, we consider a first step toward active needle steering: design and experimental validation of a nonholonomic model for steering flexible needles with bevel tips. The model generalizes the standard three degree-of-freedom (DOF) nonholonomic unicycle and bicycle models to 6 DOF using Lie group theory. Model parameters are fit using experimental data, acquired via a robotic device designed for the specific purpose of inserting and steering a flexible needle. The experiments quantitatively validate the bevel-tip needle steering model, enabling future research in flexible needle path planning, control, and simulation.
441 citations
••
01 Jan 2013TL;DR: HMP uses sparse coding to learn hierarchical feature representations from raw RGB-D data in an unsupervised way and enables superior object recognition results using linear support vector machines.
Abstract: Recently introduced RGB-D cameras are capable of providing high quality synchronized videos of both color and depth With its advanced sensing capabilities, this technology represents an opportunity to dramatically increase the capabilities of object recognition It also raises the problem of developing expressive features for the color and depth channels of these sensors In this paper we introduce hierarchical matching pursuit (HMP) for RGB-D data HMP uses sparse coding to learn hierarchical feature representations from raw RGB-D data in an unsupervised way Extensive experiments on various datasets indicate that the features learned with our approach enable superior object recognition results using linear support vector machines
395 citations