Artur Koch

Fast and Scalable CPU/GPU Collision Detection for Rigid and Deformable Surfaces

We present a new hybrid CPU/GPU collision detection technique for rigid and deformable objects based on spatial subdivision. Our approach efficiently exploits the massive computational capabilities of modern CPUs and GPUs commonly found in off‐the‐shelf computer systems. The algorithm is specifically tailored to be highly scalable on both the CPU and the GPU sides. We can compute discrete and continuous external and self‐collisions of non‐penetrating rigid and deformable objects consisting of many tens of thousands of triangles in a few milliseconds on a modern PC. Our approach is orders of magnitude faster than earlier CPU‐based approaches and up to twice as fast as the most recent GPU‐based techniques.

Efficient self-adjusting, similarity-based location fingerprinting with passive UHF RFID

In this paper we present extensive experimental results of location fingerprinting with passive UHF radio-frequency identification (RFID). As recent passive RFID hardware provides information about received signal strength (RSS), we evaluate its usefulness in the context of fingerprinting based on classical vector similarity measures. We analyze the impact of decisive parameters of the applied approach and also select them automatically via cross-validation, including the most appropriate similarity measure. A further novelty is an RSS thresholding mechanism which reduces the computational demands of comparing fingerprints. This technique is especially useful in surroundings which are densely equipped with RFID tags, such as future supermarkets or logistic centers. We conducted real-world experiments with a mobile robot and two different RFID readers. Results are reported both for global localization in each time frame and for time-filtered position tracking. We provide the experimental data of this work for download.

Multi-class fruit classification using RGB-D data for indoor robots

In this paper we present an effective and robust system to classify fruits under varying pose and lighting conditions tailored for an object recognition system on a mobile platform. Therefore, we present results on the effectiveness of our underlying segmentation method using RGB as well as depth cues for the specific technical setup of our robot. A combination of RGB low-level visual feature descriptors and 3D geometric properties is used to retrieve complementary object information for the classification task. The unified approach is validated using two multi-class RGB-D fruit categorization datasets. Experimental results compare different feature sets and classification methods and highlight the effectiveness of the proposed features using a Random Forest classifier.

Object Recognition and Tracking for Indoor Robots Using an RGB-D Sensor

In this paper, we extend and generalize our previously published approach on RGB-D based fruit recognition to be able to recognize different kinds of objects in front of our mobile system. We therefore first extend our segmentation to use depth filtering and clustering with a watershed algorithm on the depth data to detect the target to be recognized. We forward the processed data to extract RGB-D descriptors that are used to recoup complementary object information for the classification and recognition task. After having detected the object once, we apply a simple tracking method to reduce the object search space and the computational load through frequent detection queries. The proposed method is evaluated using the random forest (RF) classifier. Experimental results highlight the effectiveness as well as real-time suitability of the proposed extensions for our mobile system based on real RGB-D data.

RFID-enabled location fingerprinting based on similarity models from probabilistic similarity measures

In this work we present a novel fingerprint similarity sensor model for the purpose of localizing a mobile robot with passive ultra-high frequency (UHF) radio-frequency identification (RFID) through location fingerprinting. We firstly evaluate the performance of probabilistic similarity measures applied to received signal strength (RSS) and compare them with previous results obtained with well known vector similarity measures. We furthermore extend the observation model used in a particle filter to dynamically adapt to the uncertainty of single candidate fingerprints by using their similarity to the current observation. For this purpose, we derive a new likelihood function and introduce an alternative way of selecting candidate fingerprints using a combination of their signal space similarity as well as the distance between the currently estimated pose and reference fingerprints. Results obtained from experiments in two different environments highlight the improved accuracy as well as robustness of the proposed methods.

Salient regions detection for indoor robots using RGB-D data

The goal of saliency detection is to highlight objects in image data that stand out relative to their surrounding. Therefore, saliency detection aims to capture regions that are perceived as important. The most recent bottom-up approaches for saliency detection measure contrast based on visual features in 2D scenes, ignoring depth value. This work presents an effective method to measure saliency by mapping pixels into foreground and background regions in RGB-D images. Namely, we first segment an image into regions to evaluate the object uniqueness and consistency using graph-based segmentation. Then, we utilize the region color, depth, layout and boundary information to produce robust foreground and background saliency measures. Finally, we combine the two saliency maps based on Gaussian weights. As a result, our approach produces high-quality saliency maps, which may be used for further processing like object detection or recognition. Experimental results on two datasets compare our method with the state of the art and highlight its effectiveness.

Path following with passive UHF RFID received signal strength in unknown environments

We present a novel approach incorporating a combination of Radio-Frequency Identification (RFID) and odometry information into the motion control of a mobile robot for the purpose of path following in unknown environments. Our method utilizes RFID measurements as landmarks and makes the mobile robot autonomously follow a path that was previously recorded in a manual training phase. The approach needs no prior information about RFID sensor models, the distribution and positioning of the tags nor does it require a map of the environment. Particularly, it is adaptive to different reader power levels and various tag densities, which have a major impact on RFID performance. Extensive experiments with a SCITOS G5 robot in different environments like a library, a supermarket and hallways confirm the effectiveness of our algorithm.

Mapping UHF RFID tags with a mobile robot using a 3D sensor model

Recently, researchers showed growing interest in utilizing UHF Radio-Frequency Identification (RFID) technology for localizing tagged items with mobile robots in industrial scenarios. In this paper we present a novel three-dimensional (3D) probability sensor model of RFID antennas in the context of mapping passive RFID tags with mobile robots. The proposed 3D sensor model characterizes both detection rates and received signal strength (RSS). Compared to 2D-sensor model based approaches, the 3D model gains a higher mapping accuracy for 2D position estimation. Specially, with this sensor model, we are able to localize the tags in 3D by integrating the measurements from a pair of RFID antennas mounted at different heights of the robot. Furthermore, by integrating negative information (i.e., non-detections), the 3D mapping accuracy can be improved. Additionally, we utilize KLD-sampling to reduce the number of particles for our specific application, so that our algorithm can be performed online. Indoor experiments with a Scitos G5 robot demonstrate the effectiveness of our approach. We also provide the datasets of this work for download.