Refine
Year of publication
Institute
- Fachbereich Elektrotechnik und Informationstechnik (139) (remove)
Document Type
- Article (65)
- Conference Proceeding (65)
- Part of a Book (7)
- Book (2)
Keywords
- Autonomous mobile robots (2)
- Industry 4.0 (2)
- Multi-robot systems (2)
- Smart factory (2)
- Anomaly detection (1)
- Automation (1)
- Benchmark (1)
- Computational modeling (1)
- Control (1)
- Cyber-physical systems (1)
Many biped robots deploy a form of gait that follows the zero moment point (ZMP) approach, that is, the robot is in a stable position at any point in time. This requires the robot to be fully actuated. While very stable, the draw-backs of this approach are a fairly slow gait and high energy consumption. An alternative approach is the so-called passive-dynamic walking, where the gait makes use of the inertia and dynamic stability of the robot. In this paper we describe our ongoing work of combining the principles of passive-dynamic walking on the fully-actuated biped robot Nao, which is also deployed for robotic soccer applications. We present a simple controller that allows the robot to stably rock sidewards, showing a closed limit-cycle. We discuss first results of superimposing a forward motion on the sidewards motion. Based on this we expect to endow the Nao with a fast, robust, and stable passive-dynamic walk on the fully-actuated Nao in the future.
Embedding fuzzy controllers in golog / Ferrein, Alexander ; Schiffer, Stefan ; Lakemeyer, Gerhard
(2009)
RGB-D sensors such as the Microsoft Kinect or the Asus Xtion are inexpensive 3D sensors. A depth image is computed by calculating the distortion of a known infrared light (IR) pattern which is projected into the scene. While these sensors are great devices they have some limitations. The distance they can measure is limited and they suffer from reflection problems on transparent, shiny, or very matte and absorbing objects. If more than one RGB-D camera is used the IR patterns interfere with each other. This results in a massive loss of depth information. In this paper, we present a simple and powerful method to overcome these problems. We propose a stereo RGB-D camera system which uses the pros of RGB-D cameras and combine them with the pros of stereo camera systems. The idea is to utilize the IR images of each two sensors as a stereo pair to generate a depth map. The IR patterns emitted by IR projectors are exploited here to enhance the dense stereo matching even if the observed objects or surfaces are texture-less or transparent. The resulting disparity map is then fused with the depth map offered by the RGB-D sensor to fill the regions and the holes that appear because of interference, or due to transparent or reflective objects. Our results show that the density of depth information is increased especially for transparent, shiny or matte objects.
South Africa in recent years is the establishment of a number of research hubs involved in AI activities ranging from mobile robotics and computational intelligence, to knowledge representation and reasoning, and human language technologies. In this survey we take the reader through a quick tour of the research being conducted at these hubs, and touch on an initiative to maintain and extend the current level of interest in AI research in the country.
In this paper we present SMART-FACTORY, a setup for a research and teaching facility in industrial robotics that is based on the RoboCup Logistics League. It is driven by the need for developing and applying solutions for digital production. Digitization receives constantly increasing attention in many areas, especially in industry. The common theme is to make things smart by using intelligent computer technology. Especially in the last decade there have been many attempts to improve existing processes in factories, for example, in production logistics, also with deploying cyber-physical systems. An initiative that explores challenges and opportunities for robots in such a setting is the RoboCup Logistics League. Since its foundation in 2012 it is an international effort for research and education in an intra-warehouse logistics scenario. During seven years of competition a lot of knowledge and experience regarding autonomous robots was gained. This knowledge and experience shall provide the basis for further research in challenges of future production. The focus of our SMART-FACTORY is to create a stimulating environment for research on logistics robotics, for teaching activities in computer science and electrical engineering programmes as well as for industrial users to study and explore the feasibility of future technologies. Building on a very successful history in the RoboCup Logistics League we aim to provide stakeholders with a dedicated facility oriented at their individual needs.
Planwirtschaft
(2004)
20 Years of RoboCup
(2016)
Among many approaches to address the high-level decision making problem for autonomous robots and agents, the robot program¬ming and plan language Golog follows a logic-based deliberative approach, and its successors were successfully deployed in a number of robotics applications over the past ten years. Usually, Golog interpreter are implemented in Prolog, which is not available for our target plat¬form, the bi-ped robot platform Nao. In this paper we sketch our first approach towards a prototype implementation of a Golog interpreter in the scripting language Lua. With the example of the elevator domain we discuss how the basic action theory is specified and how we implemented fluent regression in Lua. One possible advantage of the availability of a Non-Prolog implementation of Golog could be that Golog becomes avail¬able on a larger number of platforms, and also becomes more attractive for roboticists outside the Cognitive Robotics community.
The idea of component-based software engineering was proposed more that 40 years ago, yet only few robotics software frameworks follow these ideas. The main problem with robotics software usually is that it runs on a particular platform and transferring source code to another platform is crucial. In this paper, we present our software framework Fawkes which follows the component-based software design paradigm by featuring a clear component concept with well-defined communication interfaces. We deployed Fawkes on several different robot platforms ranging from service robots to biped soccer robots. Following the component concept with clearly defined communication interfaces shows great benefit when porting robot software from one robot to the other. Fawkes comes with a number of useful plugins for tasks like timing, logging, data visualization, software configuration, and even high-level decision making. These make it particularly easy to create and to debug productive code, shortening the typical development cycle for robot software.
The high-level decision making process of an autonomous robot can be seen as an hierarchically organised entity, where strategical decisions are made on the topmost layer, while the bottom layer serves as driver for the hardware. In between is a layer with monitoring and reporting functionality. In this paper we propose a behaviour engine for this middle layer which, based on formalism of hybrid state machines (HSMs), bridges the gap between high-level strategic decision making and low-level actuator control. The behaviour engine has to execute and monitor behaviours and reports status information back to the higher level. To be able to call the behaviours or skills hierarchically, we extend the model of HSMs with dependencies and sub-skills. These Skill-HSMs are implemented in the lightweight but expressive Lua scripting language which is well-suited to implement the behaviour engine on our target platform, the humanoid robot Nao.
In order to allow an autonomous robot to perform non-trivial tasks like to explore a foreign planet the robot has to have deliberative capabilities like reasoning or planning. Logic-based approaches like the programming and planing language Golog and it successors has been successfully used for such decision-making problems. A drawback of this particular programing language is that their interpreter usually are written in Prolog and run on a Prolog back-end. Such back-ends are usually not available or feasible on resource-limited robot systems. In this paper we present our ideas and first results of a re-implementation of the interpreter based on the Lua scripting language which is available on a wide range of systems including small embedded systems.
We propose a formalism for reasoning about actions based on multi-modal logic which allows for expressing observations as first-class objects. We introduce a new modal operator, namely [o |α], which allows us to capture the notion of perceiving an observation given that an action has taken place. Formulae of the type [o |α]ϕ mean ’after perceiving observation o, given α was performed, necessarily ϕ’. In this paper, we focus on the challenges concerning sensing with explicit observations, and acting with nondeterministic effects. We present the syntax and semantics, and a correct and decidable tableau calculus for the logic
Benchmarking of various LiDAR sensors for use in self-driving vehicles in real-world environments
(2022)
Abstract
In this paper, we report on our benchmark results of the LiDAR sensors Livox Horizon, Robosense M1, Blickfeld Cube, Blickfeld Cube Range, Velodyne Velarray H800, and Innoviz Pro. The idea was to test the sensors in different typical scenarios that were defined with real-world use cases in mind, in order to find a sensor that meet the requirements of self-driving vehicles. For this, we defined static and dynamic benchmark scenarios. In the static scenarios, both LiDAR and the detection target do not move during the measurement. In dynamic scenarios, the LiDAR sensor was mounted on the vehicle which was driving toward the detection target. We tested all mentioned LiDAR sensors in both scenarios, show the results regarding the detection accuracy of the targets, and discuss their usefulness for deployment in self-driving cars.
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 combining programming the behaviour 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
Many tasks for autonomous agents or robots are best described by a specification of the environment and a specification of the available actions the agent or robot can perform. Combining such a specification with the possibility to imperatively program a robot or agent is what we call the actionbased imperative programming. One of the most successful such approaches is Golog. In this paper, we draft a proposal for a new robot programming language YAGI, which is based on the action-based imperative programming paradigm. Our goal is to design a small, portable stand-alone YAGI interpreter. We combine the benefits of a principled domain specification with a clean, small and simple programming language, which does not exploit any side-effects from the implementation language. We discuss general requirements of action-based programming languages and outline YAGI, our action-based language approach which particularly aims at embeddability.
One central challenge for self-driving cars is a proper path-planning. Once a trajectory has been found, the next challenge is to accurately and safely follow the precalculated path. The model-predictive controller (MPC) is a common approach for the lateral control of autonomous vehicles. The MPC uses a vehicle dynamics model to predict the future states of the vehicle for a given prediction horizon. However, in order to achieve real-time path control, the computational load is usually large, which leads to short prediction horizons. To deal with the computational load, the control algorithm can be parallelized on the graphics processing unit (GPU). In contrast to the widely used stochastic methods, in this paper we propose a deterministic approach based on grid search. Our approach focuses on systematically discovering the search area with different levels of granularity. To achieve this, we split the optimization algorithm into multiple iterations. The best sequence of each iteration is then used as an initial solution to the next iteration. The granularity increases, resulting in smooth and predictable steering angle sequences. We present a novel GPU-based algorithm and show its accuracy and realtime abilities with a number of real-world experiments.
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.
In this extended abstract we describe the robot programming and planning language READYLOG, a GOLOG dialect which was developed to support the decision making of robots acting in dynamic real-time domains like robotic soccer. The formal framework of READYLOG, which is based on the situation calculus, features imperative control structures like loops and procedures, allows for decision-theoretic planning, and accounts for a continuously changing world. We developed high-level controllers in READYLOG for our soccer robots in RoboCup’s Middle-size league, but also for service robots and for autonomous agents in interactive computer games.
In the RoboCup@Home domestic service robot competition, complex tasks such as "get the cup from the kitchen and bring it to the living room" or "find me this and that object in the apartment" have to be accomplished. At these competitions the robots may only be instructed by natural language. As humans use qualitative concepts such as "near" or "far", the robot needs to cope with them, too. For our domestic robot, we use the robot programming and plan language Readylog, our variant of Golog. In previous work we extended the action language Golog, which was developed for the high-level control of agents and robots, with fuzzy concepts and showed how to embed fuzzy controllers in Golog. In this paper, we demonstrate how these notions can be fruitfully applied to two domestic service robotic scenarios. In the first application, we demonstrate how qualitative fluents based on a fuzzy set semantics can be deployed. In the second program, we show an example of a fuzzy controller for a follow-a-person task.