Kai Oliver Arras

Using Boosted Features for the Detection of People in 2D Range Data

This paper addresses the problem of detecting people in two dimensional range scans. Previous approaches have mostly used pre-defined features for the detection and tracking of people. We propose an approach that utilizes a supervised learning technique to create a classifier that facilitates the detection of people. In particular, our approach applies AdaBoost to train a strong classifier from simple features of groups of neighboring beams corresponding to legs in range data. Experimental results carried out with laser range data illustrate the robustness of our approach even in cluttered office environments

People detection in RGB-D data

People detection is a key issue for robots and intelligent systems sharing a space with people. Previous works have used cameras and 2D or 3D range finders for this task. In this paper, we present a novel people detection approach for RGB-D data. We take inspiration from the Histogram of Oriented Gradients (HOG) detector to design a robust method to detect people in dense depth data, called Histogram of Oriented Depths (HOD). HOD locally encodes the direction of depth changes and relies on an depth-informed scale-space search that leads to a 3-fold acceleration of the detection process. We then propose Combo-HOD, a RGB-D detector that probabilistically combines HOD and HOG. The experiments include a comprehensive comparison with several alternative detection approaches including visual HOG, several variants of HOD, a geometric person detector for 3D point clouds, and an Haar-based AdaBoost detector. With an equal error rate of 85% in a range up to 8m, the results demonstrate the robustness of HOD and Combo-HOD on a real-world data set collected with a Kinect sensor in a populated indoor environment.

Robox at Expo.02: A large-scale installation of personal robots

In this paper we present Robox, a mobile robot designed for operation in a mass exhibition and the experience we made with its installation at the Swiss National Exhibition Expo.02. Robox is a fully autonomous mobile platform with unique multi-modal interaction capabilities, a novel approach to global localization using multiple Gaussian hypotheses, and a powerful obstacle avoidance. Eleven Robox ran for 12 hours daily from May 15 to October 20, 2002, traveling more than 3315 km and interacting with 686,000 visitors.

Multisensor on-the-fly localization: Precision and reliability for applications

This paper presents an approach for localization using geometric features from a 360 laser range finder and a monocular vision system. Its practicability under conditions of continuous localization during motion in real time (referred to as on-the-fly localization) is investigated in large-scale experiments. The features are infinite horizontal lines for the laser and vertical lines for the camera. They are extracted using physically well-grounded models for all sensors and passed to a Kalman filter for fusion and position estimation. Positioning accuracy close to subcentimeter has been achieved with an environment model requiring 30 bytes/m 2 . Already with a moderate number of matched features, the vision information was found to further increase this precision, particularly in the orientation. The results were obtained with a fully self-contained system where extensive tests with an overall length of more than 6.4 km and 150,000 localization cycles have been conducted. The final testbed for this localization system was the Computer 2000 event, an annual computer tradeshow in Lausanne, Switzerland, where during 4 days visitors could give high-level navigation commands to the robot via a web interface. This gave us the opportunity to obtain results on long-term reliability and verify the practicability of the approach under application-like conditions. Furthermore, general aspects and limitations of multisensor on-the-fly localization are discussed.

People tracking with human motion predictions from social forces

For many tasks in populated environments, robots need to keep track of current and future motion states of people. Most approaches to people tracking make weak assumptions on human motion such as constant velocity or acceleration. But even over a short period, human behavior is more complex and influenced by factors such as the intended goal, other people, objects in the environment, and social rules. This motivates the use of more sophisticated motion models for people tracking especially since humans frequently undergo lengthy occlusion events. In this paper, we consider computational models developed in the cognitive and social science communities that describe individual and collective pedestrian dynamics for tasks such as crowd behavior analysis. In particular, we integrate a model based on a social force concept into a multi-hypothesis target tracker. We show how the refined motion predictions translate into more informed probability distributions over hypotheses and finally into a more robust tracking behavior and better occlusion handling. In experiments in indoor and outdoor environments with data from a laser range finder, the social force model leads to more accurate tracking with up to two times fewer data association errors.

2D mapping of cluttered indoor environments by means of 3D perception

This paper presents a combination of a 3D laser sensor and a line-base SLAM algorithm which together produce 2D line maps of highly cluttered indoor environments. The key of the described method is the replacement of commonly used 2D laser range sensors by 3D perception. A straightforward algorithm extracts a virtual 2D scan that also contains partially occluded walls. These virtual scans are used as input for SLAM using line segments as features. The paper presents the used algorithms and experimental results that were made in a former industrial bakery. The focus lies on scenes that are known to be problematic for pure 2D systems. The results demonstrate that mapping indoor environments can be made robust with respect to both, poor odometry and clutter.

People tracking in RGB-D data with on-line boosted target models

People tracking is a key component for robots that are deployed in populated environments. Previous works have used cameras and 2D and 3D range finders for this task. In this paper, we present a 3D people detection and tracking approach using RGB-D data. We combine a novel multi-cue person detector for RGB-D data with an on-line detector that learns individual target models. The two detectors are integrated into a decisional framework with a multi-hypothesis tracker that controls on-line learning through a track interpretation feedback. For on-line learning, we take a boosting approach using three types of RGB-D features and a confidence maximization search in 3D space. The approach is general in that it neither relies on background learning nor a ground plane assumption. For the evaluation, we collect data in a populated indoor environment using a setup of three Microsoft Kinect sensors with a joint field of view. The results demonstrate reliable 3D tracking of people in RGB-D data and show how the framework is able to avoid drift of the on-line detector and increase the overall tracking performance.

Efficient people tracking in laser range data using a multi-hypothesis leg-tracker with adaptive occlusion probabilities

We present an approach to laser-based people tracking using a multi-hypothesis tracker that detects and tracks legs separately with Kalman filters, constant velocity motion models, and a multi-hypothesis data association strategy. People are defined as high-level tracks consisting of two legs that are found with little model knowledge. We extend the data association so that it explicitly handles track occlusions in addition to detections and deletions. Additionally, we adapt the corresponding probabilities in a situation-dependent fashion so as to reflect the fact that legs frequently occlude each other. Experimental results carried out with a mobile robot illustrate that our approach can robustly and efficiently track multiple people even in situations of high levels of occlusion.

Real-time obstacle avoidance for polygonal robots with a reduced dynamic window

In this paper we present an approach to obstacle avoidance and local path planning for polygonal robots. It decomposes the task into a model stage and a planning stage. The model stage accounts for robot shape and dynamics using a reduced dynamic window. The planning stage produces collision-free local paths with a velocity profile. We present an analytical solution to the distance to collision problem for polygonal robots, avoiding thus the use of look-up tables. The approach has been tested in simulation and on two non-holonomic rectangular robots where a cycle time of 10 Hz was reached under full CPU load. During a long-term experiment over 5 km travel distance, the method demonstrated its practicability.

Feature-based multi-hypothesis localization and tracking using geometric constraints

Mobile robot localization deals with uncertain sensory information as well as uncertain data association. In this paper we present a probabilistic feature-based approach to global localization and pose tracking which explicitly addresses both problems. Location hypotheses are represented as Gaussian distributions. Hypotheses are found by a search in the tree of possible local-to-global feature associations, given a local map of observed features and a global map of the environment. During tree traversal, several types of geometric constraints are used to determine statistically feasible associations. As soon as hypotheses are available, they are tracked using the same constraint-based technique. Track splitting is performed when location ambiguity arises from uncertainties and sensing. This yields a very robust localization technique which can deal with significant errors from odometry, collisions and kidnapping. Experiments in simulation and with a real robot demonstrate these properties at low computational costs.