Robot Builders

Researchers at University College London (UCL) have written a computer program using neural networks which are duped by optical illusions the same way as we do. Their virtual robots, which were trained to ’see’ like us, could help to understand why we fall for optical illusions. This might also be important for robot vision. If robots are trained to ’see’ like us, they will act like us — and make mistakes. Very interesting… read story

This paper considers the problem of the dynamic processing of large amounts of sparse three-dimensional data. It is assumed that computations are performed in a neighborhood defined around each point in order to retrieve local properties. This general kind of processing can be applied to a wide variety of problems. A new, efficient data structure and corresponding algorithms are proposed that significantly improve the speed of the range search operation and that are suitable for on-line operation where data is accumulated dynamically. The method relies on taking advantage of overlapping neighborhoods and the reuse of previously computed data as the algorithm scans each data point. To demonstrate the dynamic capabilities of the data structure, data obtained from a laser radar mounted on a ground mobile robot operating in complex, outdoor environments is used. It is shown that this approach considerably improves the speed of an established 3-D perception processing algorithm.

read story

E! Online says that the new Transformers Sequel is a Go! The movie will again have the Michael Bay and Steven Spielburg director/producer team. People either loved or hated the first movie but if you loved the first one it’ll likely be more of the same! However, they say you’ll have to wait until June 26, 2009 (which probably means July 4th again)! If you dig deeper, it looks like no one has signed up yet and there’s plenty of spats and such behind the scenes. Will it happen? You’ll just have to wait to find out! In other news, it looks like Knight Rider will be returning to the small screen! They say that it’s Transformers inspired! What does that mean? Seems that there will be good cars and evil cars all shape shifting and generally trying to be all bad. Hopefully the show won’t be bad. Anyway, Hoffmann won’t likely be the ham in the talking car this time as he has other fish to fry. Oh, and has anyone seen the new Bionic Woman yet? It’s virtually a smorgasBORG of robotic entertainment! -more-

Researchers at University College London (UCL) have written a computer program using neural networks which are duped by optical illusions the same way as we do. Their virtual robots, which were trained to ’see’ like us, could help to understand why we fall for optical illusions. This might also be important for robot vision. If robots are trained to ’see’ like us, they will act like us — and make mistakes. Very interesting… read story

This paper proposes a real-time, robust and effective tracking framework for visual servoing applications. The algorithm is based on the fusion of visual cues and on the estimation of a transformation (either a homography or a 3D pose). The parameters of this transformation are estimated using a non-linear minimization of a unique criterion that integrates information both on the texture and the edges of the tracked object. The proposed tracker is more robust and performs well in conditions where methods based on a single cue fail. The framework has been tested for 2D object motion estimation and pose computation. The method presented in this paper has been validated on several video sequences as well as in visual servoing experiments considering various objects. Results show the method to be robust to occlusions or textured backgrounds and suitable for visual servoing applications.

read story

E! Online says that the new Transformers Sequel is a Go! The movie will again have the Michael Bay and Steven Spielburg director/producer team. People either loved or hated the first movie but if you loved the first one it’ll likely be more of the same! However, they say you’ll have to wait until June 26, 2009 (which probably means July 4th again)! If you dig deeper, it looks like no one has signed up yet and there’s plenty of spats and such behind the scenes. Will it happen? You’ll just have to wait to find out! In other news, it looks like Knight Rider will be returning to the small screen! They say that it’s Transformers inspired! What does that mean? Seems that there will be good cars and evil cars all shape shifting and generally trying to be all bad. Hopefully the show won’t be bad. Anyway, Hoffmann won’t likely be the ham in the talking car this time as he has other fish to fry. Oh, and has anyone seen the new Bionic Woman yet? It’s virtually a smorgasBORG of robotic entertainment! -more-

In this paper, an algorithm for autonomous stair climbing with a tracked vehicle is presented. The proposed method achieves robust performance under real-world conditions, without assuming prior knowledge of the stair geometry, the dynamics of the vehicle’s interaction with the stair surface, or lighting conditions. The approach relies on fast and accurate estimation of the robot’s heading and its position relative to the stair boundaries. An extended Kalman filter is used for quaternion-based attitude estimation, fusing rotational velocity measurements from a 3-axial gyroscope, and measurements of the stair edges acquired with an onboard camera. A two-tiered controller, comprised of a centering- and a heading-control module, utilizes the estimates to guide the robot rapidly, safely, and accurately upstairs. Both the theoretical analysis and implementation of the algorithm are presented in detail, and extensive experimental results demonstrating the algorithm’s performance are described.

This paper presents a distributed control algorithm for multi-target surveillance by multiple robots. Robots equipped with sensors and communication devices discover and track as many evasive targets as possible in an open region. The algorithm utilizes information from sensors, communication, and a mechanism to predict the minimum time before a robot loses a target. Workload is shared locally between robots using a greedy assignment of targets. Across long distances robots cooperate through explicit communication. The approach is coined Behavioral Cooperative Multi-robot Observation of Multiple Moving Targets. A formal representation of the proposed algorithm as well as proofs of performance guarantee are provided. Extensive simulations confirm the theoretical results in practice.

Many research teams around the world are building nanodevices of some kind. But these very small devices need very small sources of power to be fully functional. Now, researchers at the University of Illinois at Urbana-Champaign (UIUC) have shown that a single nanowire can produce power by harvesting mechanical energy from its environment. ‘Made of piezoelectric material, the nanowire generates a voltage when mechanically deformed.’ But don’t think that this nanowire, made of an oxide of barium and titanium, and measuring approximately 280 nanometers in diameter and 15 microns long, will be able to power anything more than a nanoscale sensor. It was able to generate an electrical energy of about 0.3 attojoules — less than one quintillionth of a joule or about 2.8E-25 kilowatt-hour.

A new technique for processing ultrasonic arc maps is proposed and compared to six existing techniques for map-building purposes. These techniques are simple point marking along the line-of-sight, voting and thresholding, morphological processing, Bayesian update scheme for occupancy grids, arc-transversal median algorithm, and triangulation-based fusion. The directional maximum technique, newly proposed in this paper, employs directional processing to extract the map of the environment from ultrasonic arc maps. It aims at overcoming the intrinsic angular uncertainty of ultrasonic sensors in map building, as well as eliminating noise and cross-talk related misreadings. The compared techniques are implemented with a wall-following motion-planning scheme for ground coverage. The comparison is based on experimental data and three complementary error criteria: mean absolute error, correct detection rate for full and empty regions, and computational cost in terms of CPU time. The directional maximum technique offers a very good compromise between mean absolute error and correct detection rate, with a processing time less than one-tenth of a second. Compared to the existing techniques, the directional maximum method is also superior in range accuracy and in eliminating artifacts, resulting in the best overall performance. The results indicate several trade-offs in the choice of ultrasonic arc-map processing techniques.

read story