Papers by Stefan Schiffer
A Self-Driving Car Architecture in ROS2
2020 International SAUPEC/RobMech/PRASA Conference, 2020
In this paper we report on an architecture for a self-driving car that is based on ROS2. Self-dri... more In this paper we report on an architecture for a self-driving car that is based on ROS2. Self-driving cars have to take decisions based on their sensory input in real-time, providing high reliability with a strong demand in functional safety. In principle, self-driving cars are robots. However, typical robot software, in general, and the previous version of the Robot Operating System (ROS), in particular, does not always meet these requirements. With the successor ROS2 the situation has changed and it might be considered as a solution for automated and autonomous driving. Existing robotic software based on ROS was not ready for safety critical applications like self-driving cars. We propose an architecture for using ROS2 for a self-driving car that enables safe and reliable real-time behaviour, but keeping the advantages of ROS such as a distributed architecture and standardised message types. First experiments with an automated real passenger car at lower and higher speed-levels show that our approach seems feasible for autonomous driving under the necessary real-time conditions.
Proceedings of the 4th International Conference on Agents and Artificial Intelligence, 2012
In this paper, we propose a system for robust and flexible command interpretation on a mobile rob... more In this paper, we propose a system for robust and flexible command interpretation on a mobile robot in domestic service robotics applications. Existing language processing for instructing a mobile robot often make use of a simple, restricted grammar where precisely pre-defined utterances are directly mapped to system calls. This does not take into account fallibility of human users and only allows for binary processing; either a command is part of the grammar and hence understood correctly, or it is not part of the grammar and gets rejected. We model the language processing as an interpretation process where the utterance needs to be mapped to a robot's capabilities. We do so by casting the processing as a (decision-theoretic) planning problem on interpretatory actions. This allows for a flexible system that can resolve ambiguities and which is also capable of initiating steps to achieve clarification.
International Journal of Advanced Robotic Systems, 2016
Robots are widely used as a vehicle to spark interest in science and technology in learners. A nu... more Robots are widely used as a vehicle to spark interest in science and technology in learners. A number of initiatives focus on this issue, for instance, the Roberta Initiative, the FIRST Lego League, the World Robot Olympiad and RoboCup Junior. Robotic competitions are valuable not only for school learners but also for university students, as the RoboCup initiative shows. Besides technical skills, the students get some project exposure and experience what it means to finish their tasks on time. But qualifying students for future high-tech areas should not only be for students from developed countries. In this article, we present our experiences with research and education in robotics within the RoboCup initiative, in Germany and South Africa; we report on our experiences with trying to get the RoboCup initiative in South Africa going. RoboCup has a huge support base of academic institutions in Germany; this is not the case in South Africa. We present our ‘north–south’ collaboration i...
Lecture Notes in Computer Science, 2016
For mapping with mobile robots the fast acquisition of dense point clouds is important. Different... more For mapping with mobile robots the fast acquisition of dense point clouds is important. Different sensor techniques and devices exist for different applications. In this paper, we present a novel platform for rotating 3D and 2D LiDAR sensors. It allows for swiftly capturing 3D scans that are densely populated and that almost cover a full sphere. While the platform design is generic and many common LRF can be mounted on it, in our setup we use a Velodyne VLP-16 PUCK LiDAR as well as a Hokuyo UTM-30LX-EW LRF to acquire distance measurements. We describe the hardware design as well as the control software. We further compare our system with other existing commercial and non-commercial designs, especially with the FARO Focus 3D X 130.
Lecture Notes in Computer Science, 2012
Much of the existing work on plan recognition assumes that actions of other agents can be observe... more Much of the existing work on plan recognition assumes that actions of other agents can be observed directly. In continuous temporal domains such as traffic scenarios this assumption is typically not warranted. Instead, one is only able to observe facts about the world such as vehicle positions at different points in time, from which the agents' plans need to be inferred. In this paper we show how this problem can be addressed in the situation calculus and a new variant of the action programming language Golog, which includes features such as continuous time and change, stochastic actions, nondeterminism, and concurrency. In our approach we match observations against a set of candidate plans in the form of Golog programs. We turn the observations into actions which are then executed concurrently with the given programs. Using decision-theoretic optimization techniques those programs are preferred which bring about the observations at the appropriate times. Besides defining this new variant of Golog we also discuss an implementation and experimental results using driving maneuvers as an example.
Communications in Computer and Information Science, 2013
In this paper, we propose a flexible system for robust natural language interpretation of spoken ... more In this paper, we propose a flexible system for robust natural language interpretation of spoken commands on a mobile robot in domestic service robotics applications. Existing language processing for instructing a mobile robot is often restricted by using a simple grammar where precisely pre-defined utterances are directly mapped to system calls. These approaches do not regard fallibility of human users and they only allow for binary processing of an utterance; either a command is part of the grammar and hence understood correctly, or it is not part of the grammar and gets rejected. We model the language processing as an interpretation process where the utterance needs to be mapped to the robot's capabilities. We do so by casting the processing as a (decisiontheoretic) planning problem on interpretation actions. This allows for a flexible system that can resolve ambiguities and which is also capable of initiating steps to achieve clarification. We show how we evaluated several versions of the system with multiple utterances of different complexity as well as with incomplete and erroneous requests.
Lecture Notes in Computer Science, 2008
Specifying the behavior of an intelligent autonomous robot or agent is a non-trivial task. The qu... more Specifying the behavior of an intelligent autonomous robot or agent is a non-trivial task. The question is: how can the knowledge of the domain expert be encoded in the agent program? Qualitative representations in general facilitate to express the knowledge of a domain expert. In this paper, we propose a semantics for qualitative fluents in the situation calculus. Our semantics is based on fuzzy sets. Membership functions define to which degree a qualitative fluent belongs to a particular category. Especially intriguing about a fuzzy set semantics for qualitative fluents is that the qualitative ranges may overlap, and a value can, at the same time, fall into several categories.
2009 IEEE International Conference on Fuzzy Systems, 2009
High-level behaviour specification of an intelligent autonomous agent or robot is a non-trivial t... more High-level behaviour specification of an intelligent autonomous agent or robot is a non-trivial task. Various approaches exist some of which try to combine different paradigms like programming and planning. In this paper, we show how to integrate fuzzy logic controllers into the logic-based programming language Golog. Golog already allows for combining programming and planning. By adding the instrument of fuzzy controllers we provide the means to have a natural specification of rules for tasks that require a high amount of reactivity. Since the facilities already present in Golog remain, we add to an already powerful framework thus expanding the applicability of Golog for high-level behaviour specification of a robot or agent.
Lecture Notes in Computer Science, 2010
Benchmarking robotic technologies is of utmost importance for actual deployment of robotic applic... more Benchmarking robotic technologies is of utmost importance for actual deployment of robotic applications in industrial and everyday environments, therefore many efforts have recently focused on this problem. Among the many different ways of benchmarking robotic systems, scientific competitions are recognized as one of the most effective ways of rapid development of scientific progress in a field. The ROBOCUP@HOME league targets the development and deployment of autonomous service and assistive robot technology, being essential for future personal domestic applications, and offers an important approach to benchmarking domestic and service robots. In this paper we present the new methodology for benchmarking DSR adopted in RoboCup@Home, that includes the definition of multiple benchmarks (tests) and of performance metrics based on the relationships between key abilities required to the robots and the tests. We also discuss the results of our benchmarking approach over the past years and provide an outlook on short-and mid-term goals of @HOME and of DSR in general.
Transportation Research Part C: Emerging Technologies, 2012
Traffic information systems have to process and analyze huge amounts of data in real-time to effe... more Traffic information systems have to process and analyze huge amounts of data in real-time to effectively provide traffic information to road users. Progress in mobile communication technology with higher bandwidths and lower latencies enables the use of data provided by in-car sensors. Data stream management systems have been proposed to address the challenges of such applications which have to process a continuous data flow from various data sources in real-time. Data mining methods, adapted to data streams, can be used to analyze the data and to identify interesting patterns such as congestion or road hazards. Although several data stream mining methods have been proposed, an evaluation of such methods in the context of traffic applications is yet missing. In this paper, we present an evaluation framework for traffic information systems based on data streams. We apply a traffic simulation software to emulate the generation of traffic data by mobile probes. The framework is applied in two case studies, namely queue-end detection and traffic state estimation. The results show which parameters of the traffic information system significantly impact the accuracy of the predicted traffic information. This provides important findings for the design and implementation of traffic information systems using data from mobile probes.
Intelligent Service Robotics, 2012
In this paper we present Caesar, an intelligent domestic service robot. In domestic settings for ... more In this paper we present Caesar, an intelligent domestic service robot. In domestic settings for service robots complex tasks have to be accomplished. Those tasks benefit from deliberation, from robust action execution and from flexible methods for human-robot interaction that account for qualitative notions used in natural language as well as human fallibility. Our robot Caesar deploys AI techniques on several levels of its system architecture. On the low-level side, system modules for localization or navigation make, for instance, use of path planning methods, heuristic search, and Bayesian filters. For face recognition and humanmachine interaction, random trees and well-known methods from natural language processing are deployed. For deliberation, we use the robot programming and plan language Readylog, which was developed for the high-level control of agents and robots; it allows to combine programming the behaviour with using planning to find a course of action. Readylog is a variant of the robot programming language Golog. We extended Readylog to be able to cope with qualitative notions of space frequently used by humans such as "near" and "far". This facilitates human-robot interaction by bridging the gap between human natural language and the numerical values needed by the robot. Further, we use Readylog to increase the flexible interpretation of human commands with decision-theoretic planning. We give an overview of the different methods deployed in Caesar and show the applicability of a system equipped with these AI techniques in domestic service robotics.
In this paper we present Caesar, an intelligent domestic service robot. In domestic settings for ... more In this paper we present Caesar, an intelligent domestic service robot. In domestic settings for service robots complex tasks have to be accomplished. Those tasks benefit from deliberation, from robust action execution and from flexible methods for human-robot interaction that account for qualitative notions used in natural language as well as human fallibility. Our robot Caesar deploys AI techniques on several levels of its system architecture. On the low-level side, system modules for localization or navigation make, for instance, use of path planning methods, heuristic search, and Bayesian filters. For face recognition and human-machine interaction, random trees and well-known methods from natural language processing are deployed. For deliberation, we use the robot programming and plan language Readylog, which was developed for the high-level control of agents and robots; it allows to combine programming the behaviour with using planning to find a course of action. Readylog is a ...
Mobile robots, in general, and service robots in human en-vironments, in particular, need to have... more Mobile robots, in general, and service robots in human en-vironments, in particular, need to have versatile abilities to perceive and interact with their environment. Biologically in-spired sound source localization is an interesting ability for such a robot. When combined with other sensory input both the sound localization and the general interaction abilities can be improved. In particular, spatial filtering can be used to im-prove the signal-to-noise ratio of speech signals emanating from a given direction in order to enhance speech recognition abilities. In this paper we investigate and discuss the com-bination of sound source localization and laser-based object recognition on a mobile robot.
Abstract. This paper describes an interactive demonstration by the AllemaniACs ’ domestic service... more Abstract. This paper describes an interactive demonstration by the AllemaniACs ’ domestic service robot Caesar. In a home-like environment Caesar’s task is to help setting the table. Besides basic capabilities of an autonomous mobile robot it uses methods for human-robot interaction and it also has a sophisticated high-level control that allows for decision-theoretic planning. We use this demo to illustrate the interplay of several modules of our robot control software in carrying out complex tasks. The overall system allows to perform robust reliable service robotics in domestic settings like in the RoboCup@Home league. Also, we show how our high-level programming language provides a powerful framework for agent behavior specification that can be beneficially deployed for service robotic applications. The system was showcased repeatedly, most notably at a national RoboCup competition and at an international conference. 1
Abstract. In order to make a robot execute a given task plan more robustly we want to enable it t... more Abstract. In order to make a robot execute a given task plan more robustly we want to enable it to take care of its self-maintenance requirements during online execution of this program. This requires the robot to know about the (internal) states of its components, constraints that restrict execution of certain actions and possibly also how to recover from faulty situations. The general idea is to implement a transformation process on the plans, which are specified in the agent programming language ReadyLog, to be performed based on explicit (temporal) constraints. Afterwards, a ’guarded ’ execution of the transformed program should result in more robust behavior. 1
All in-text references underlined in blue are linked to publications on ResearchGate, letting you... more All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.
Machine learning based 3D object detection for navigation in unstructured environments
2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)
Abstract. Until now world models in robotic soccer have been mainly quantita-tive in nature, cons... more Abstract. Until now world models in robotic soccer have been mainly quantita-tive in nature, consisting of fine-grained (numerical) estimates of player positions, ball trajectories, and the like. In contrast, the concepts used in human soccer are largely qualitative. Moving to qualitative world models also for robots has the advantage that it drastically reduces the space of possible game situations that need to be considered and, provided the concepts correspond to those in human soccer theory, it eases the task of agent specification for the designer. In this pa-per we propose qualitative representations using ideas from spatial cognition and employing Voronoi diagrams. We also discuss how reasoning with these repre-sentations is achieved within our underlying agent programming framework. 1
Compiling ROS Schooling Curricula via Contentual Taxonomies
Uploads
Papers by Stefan Schiffer