We present our vision-based system for grasping novel objects in cluttered environments. Our system can be divided into four components: 1) decide where to grasp an object, 2) perceive obstacles, 3) plan an obstacle-f...
详细信息
ISBN:
(纸本)9783642147432
We present our vision-based system for grasping novel objects in cluttered environments. Our system can be divided into four components: 1) decide where to grasp an object, 2) perceive obstacles, 3) plan an obstacle-free path, and 4) follow the path to grasp the object. While most prior work assumes availability of a detailed 3-d model of the environment, our system focuses on developing algorithms that are robust to uncertainty and missing data, which is the case in real-world experiments. In this paper, we test our robotic grasping system using our STAIR. (STanford Al Robots) platforms on two experiments: grasping novel objects and unloading items from a dishwasher. We also illustrate these ideas in the context of having a robot fetch an object from another room in response to a verbal request.
Assembly partitioning with an infinite translation is the application of an infinite translation to partition an assembled product into two complementing subsets of parts, referred to as a subassemblies, each treated ...
详细信息
ISBN:
(纸本)9783642003110
Assembly partitioning with an infinite translation is the application of an infinite translation to partition an assembled product into two complementing subsets of parts, referred to as a subassemblies, each treated as a rigid body. We present an exact implementation of an efficient algorithm to obtain such a motion and subassemblies given an assembly of polyhedra in R(3). We do not assume general position. Namely, we handle degenerate input, and produce exact results. As often occurs, motions that partition a given assembly or subassembly might be isolated in the infinite space of motions. Any perturbation of the input or of intermediate results, caused by, for example, imprecision, might result with dismissal of valid partitioning-motions. In the extreme case, where there is only a finite number of valid partitioning-motions, no motion may be found, even though such exists. The implementation is based on software components that have been developed and introduced only recently. They paved the way to a complete, efficient, and concise implementation. Additional information is available at http://***/projects/internal-projects/assembly-partitioning/project-page.
To increase the maximum payload, the joint arrangement of the Stewart platform type leg mechanism for a biped walking vehicle is optimized by a dynamic simulation and a real-coded genetic algorithm. Using effective jo...
详细信息
ISBN:
(纸本)9783642147432
To increase the maximum payload, the joint arrangement of the Stewart platform type leg mechanism for a biped walking vehicle is optimized by a dynamic simulation and a real-coded genetic algorithm. Using effective joint arrangement, the maximum HMS (root-mean-square) value of the current will be able to be reduced. A new prototype of a biped walking vehicle, WL-16RIV, was developed by using the optimal joint arrangement method. Weight saving in some parts was also conducted. Through walking experiments, the maximum R,MS value of the current, was reduced, and the maximum payload was increased. The effectiveness of the proposed method was confirmed
We consider how the tedious chore of folding clothes can be performed by a robot. At the core of our approach is the definition of a cloth model that allows us to reason about the geometry rather than the physics of t...
详细信息
ISBN:
(纸本)9783642174513
We consider how the tedious chore of folding clothes can be performed by a robot. At the core of our approach is the definition of a cloth model that allows us to reason about the geometry rather than the physics of the cloth in significant parts of the state space. We present an algorithm that, given the geometry of the cloth, computes how many grippers are needed and what the motion of these grippers are to achieve a final configuration specified as a sequence of g-folds folds that can be achieved while staying in the subset of the state space to which the geometric model applies. G-folds are easy to specify and are sufficiently rich to capture most common cloth folding procedures. We consider folds involving single and stacked layers of material and describe experiments folding towels, shirts, sweaters, and slacks with a Willow Garage PR2 robot. Experiments based on the planner had success rates varying between 5/9 and 9/9 for different clothing articles.
Fujitsu has been conducting ongoing research and development in robotics to enable robots to support people and make their lives safer and more comfortable. In this paper, we present our commercial service robot "...
详细信息
ISBN:
(纸本)9783642147432
Fujitsu has been conducting ongoing research and development in robotics to enable robots to support people and make their lives safer and more comfortable. In this paper, we present our commercial service robot "enon" and its 3D vision system. The robot, with left and right arms that give live degrees of freedom (DOF) and grippers, a pan-tilt mechanism carrying six cameras, and a wheel mechanism, can operate efficiently and provides services in a variety of places such as offices and public facilities. The vision system employs a dedicated FPGA processor to accelerate the image processing functions required for autonomous navigation. Its power consumption is only 10 W, about a seventh that of a typical Pentium (R) 4 personal computer, while the processing speed for correlation matching is roughly three times faster than such a system. This paper also introduces our stereovision ASIC, newly developed to enhance the performance of our vision system.
In this paper we propose a computationally efficient method for the steering of flexible needles with a bevel tip in the presence of uncertainties for the case when there are no obstacles in the environment. Based on ...
详细信息
ISBN:
(纸本)9783642003110
In this paper we propose a computationally efficient method for the steering of flexible needles with a bevel tip in the presence of uncertainties for the case when there are no obstacles in the environment. Based on the stochastic model for the needles, we develop a new framework for path planning of a flexible needle with a bevel tip. This consists of three parts: (a) approximation of probability density functions for the needle tip pose;(b) application of a second order error propagation algorithm on the Euclidean motion group;and (c) application of the path-of-probability (POP) algorithm. The probability density functions are approximated as Gaussians under the assumption that the uncertainty in the needle insertion is fairly small. The means and the covariances for the probability density functions are estimated using the error propagation algorithm that has second order accuracy. The POP algorithm is adapted to the path planning for the flexible needles so as to give the appropriate steering plan. Combining these components and considering 5 degree-of-freedom targets, the new method gives the path of the flexible needle that hits the target point with the desired hitting direction.
This paper explores a topological perspective of planning. A series of examples and theorems establishes a fundamental coupling between tasks on graphs and simplicial complexes. Planning under uncertainty is one appli...
详细信息
ISBN:
(纸本)9783642003110
This paper explores a topological perspective of planning. A series of examples and theorems establishes a fundamental coupling between tasks on graphs and simplicial complexes. Planning under uncertainty is one application. The paper introduces strategy and loopback complexes. The paper's main theorem shows that tasks specified by goal states in nondeterministic graphs have guaranteed solutions if and only if their loopback complexes are homotopic to spheres.
Interval analysis is a relatively new mathematical tool that allows one to deal with problems that may have to be solved numerically with a computer. Examples of such problems are system solving and global optimizatio...
详细信息
ISBN:
(纸本)9783642147432
Interval analysis is a relatively new mathematical tool that allows one to deal with problems that may have to be solved numerically with a computer. Examples of such problems are system solving and global optimization but numerous other problems may be addressed as well. This approach has the following general advantages: it allows to find solutions of a problem only within some finite domain numerical computer round-off errors are taken into account so that the solutions are guaranteed A further inherent property that is of interest for robotics problems is that this approach allows one to deal with the uncertainties that are unavoidable in robotics. Although the basic principles of interval analysis are easy to understand and to implement, this approach will be efficient only if additional methods are used and if the problem at hand is formulated appropriately. In this paper we will emphasize various robotics problems that have been solved with interval analysis, many of which are currently beyond the reach of other mathematical approaches.
We propose a novel enhancement to the task of collision-testing a set of local paths. Our approach circumvents expensive collision-tests, yet it declares a continuum of paths collision-free by exploiting both the stru...
详细信息
ISBN:
(纸本)9783642174513
We propose a novel enhancement to the task of collision-testing a set of local paths. Our approach circumvents expensive collision-tests, yet it declares a continuum of paths collision-free by exploiting both the structure of paths and the outcome of previous tests. We define a homotopy-like equivalence relation among local paths and provide algorithms to (1) classify paths based on equivalence, and (2) implicitly collision-test up to 90% of them. We then prove both correctness and completeness of these algorithms before providing experimental results showing a performance increase up to 300%.
暂无评论