Author name cluster

Anna Yershova

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

ICRA Conference 2014 Conference Paper

Head tracking for the Oculus Rift

Steven M. LaValle
Anna Yershova
Max Katsev
Michael Antonov

We present methods for efficiently maintaining human head orientation using low-cost MEMS sensors. We particularly address gyroscope integration and compensation of dead reckoning errors using gravity and magnetic fields. Although these problems have been well-studied, our performance criteria are particularly tuned to optimize user experience while tracking head movement in the Oculus Rift Development Kit, which is the most widely used virtual reality headset to date. We also present novel predictive tracking methods that dramatically reduce effective latency (time lag), which further improves the user experience. Experimental results are shown, along with ongoing research on positional tracking.

Details

IROS Conference 2005 Conference Paper

Adaptive tuning of the sampling domain for dynamic-domain RRTs

Leonard Jaillet
Anna Yershova
Steven M. LaValle
Thierry Siméon

Sampling based planners have become increasingly efficient in solving the problems of classical motion planning and its applications. In particular, techniques based on the rapidly-exploring random trees (RRTs) have generated highly successful single-query planners. Recently, a variant of this planner called dynamic-domain RRT was introduced by Yershova et al. (2005). It relies on a new sampling scheme that improves the performance of the RRT approach on many motion planning problems. One of the drawbacks of this method is that it introduces a new parameter that requires careful tuning. In this paper we analyze the influence of this parameter and propose a new variant of the dynamic-domain RRT, which iteratively adapts the sampling domain for the Voronoi region of each node during the search process. This allows automatic tuning of the parameter and significantly increases the robustness of the algorithm. The resulting variant of the algorithm has been tested on several path planning problems.

Details

AAAI Conference 2005 Conference Paper

Bitbots: Simple Robots Solving Complex Tasks

Anna Yershova
Robert Ghrist

Sensing uncertainty is a central issue in robotics. Sensor limitations often prevent accurate state estimation, and robots find themselves confronted with a complicated information (belief) space. In this paper we define and characterize the information spaces of very simple robots, called Bitbots, which have severe sensor limitations. While complete estimation of the robot’s state is impossible, careful consideration and management of the uncertainty is presented as a search in the information space. We show that these simple robots can solve several challenging online problems, even though they can neither obtain a complete map of their environment nor exactly localize themselves. However, when placed in an unknown environment, Bitbots can build a topological representation of it and then perform pursuitevasion (i. e. , locate all moving targets inside this environment). This paper introduces Bitbots, and provides both theoretical analysis of their information spaces and simulation results.

PDF Details

ICRA Conference 2005 Conference Paper

Dynamic-Domain RRTs: Efficient Exploration by Controlling the Sampling Domain

Anna Yershova
Leonard Jaillet
Thierry Siméon
Steven M. LaValle

Sampling-based planners have solved difficult problems in many applications of motion planning in recent years. In particular, techniques based on the Rapidly-exploring Random Trees (RRTs) have generated highly successful single-query planners. Even though RRTs work well on many problems, they have weaknesses which cause them to explore slowly when the sampling domain is not well adapted to the problem. In this paper we characterize these issues and propose a general framework for minimizing their effect. We develop and implement a simple new planner which shows significant improvement over existing RRT-based planners. In the worst cases, the performance appears to be only slightly worse in comparison to the original RRT, and for many problems it performs orders of magnitude better.

Details

ICRA Conference 2004 Conference Paper

Deterministic Sampling Methods for Spheres and SO(3)

Anna Yershova
Steven M. LaValle

This paper addresses the problem of generating uniform deterministic samples over the spheres and the three-dimensional rotation group, SO(3). The target applications include motion planning, optimization, and verification problems in robotics and in related areas, such as graphics, control theory and computational biology. We introduce an infinite sequence of samples that is shown to achieve: 1) low-dispersion, which aids in the development of resolution complete algorithms, 2) lattice structure, which allows easy neighbor identification that is comparable to what is obtained for a grid in /spl Ropf//sup d/, and 3) incremental quality, which is similar to that obtained by random sampling. The sequence is demonstrated in a sampling-based motion planning algorithm.

Details