Although embodied AI systems are increasingly developed and tested in public environments, their influence on the design of products for older adults remains underexplored. We examine how different types of embodiment, or form factor, shape initial encounters between humans and AI when conversational abilities are comparable. Building on prior work, we conducted a two-day field study at a senior citizens’ fair in Germany (n = 25, age 24–90), where participants interacted with the screen-based avatar Ann-Sophie and the humanoid robot Ameca. Both used LLM-based dialogue systems, enabling a focus on embodied interaction rather than linguistic performance. Qualitative results show contrasting affective and social responses: Ameca’s physical presence and gaze dynamics were described as both fascinating and unsettling, while Ann-Sophie was perceived as warm but socially limited. These findings highlight the role of embodiment in shaping comfort, expectations, and ethical awareness in public human–AI interaction.

Accurate estimation of above-ground biomass is vital to improve agricultural productivity, support breeding programs, and advancing the understanding of crop physiology. Traditional measurement techniques are often labor-intensive, time-consuming, and unsuitable for large-scale applications. LiDAR offers a non-destructive and scalable alternative by capturing detailed 3D plant structures. In this work, AgriFormer is introduced, a novel deep learning framework designed to enhance AGB prediction from 3D LiDAR point clouds. AgriFormer builds upon BioNet framework and employs a multi-scale feature extraction strategy to better capture structural and contextual information from plant data. Evaluated on a public wheat and triticale dataset, AgriFormer significantly outperforms existing approaches, reducing the RMSE from 99.33 to 82.8. These results demonstrate the potential of advanced deep learning techniques for accurate and efficient digital biomass assessment in precision agriculture.

Large language models (LLMs), when integrated into social robots, have the potential to transform robot-assisted language learning by offering personalized, interactive communication. However, there is limited research exploring their potential to simultaneously reduce anxiety and enhance language-speaking skills among international university students, who often feel anxious when speaking a foreign language. This study addresses this gap by evaluating the impact of a humanoid robot powered by the OpenChat-3.5 LLM as a tandem partner for German language learning. Using a between-subjects design with 22 multilingual participants, two interaction conditions were tested: immersive (German-only) and bilingual (German-English). Our findings indicate that participants in the immersive mode reported experiencing significantly reduced perceived judgment by the robot compared to the bilingual mode. Although female participants showed a trend of greater improvement in learning gain, no significant gender differences were found. Open-ended feedback highlighted the need for enhanced contextual responses, slower speech rate, faster response times, and error corrections to enhance language speaking support. This study aims to advance social robots for learning by demonstrating the usage of generative AI in creating non-judgmental language practice scenarios.

Backstory enriches the depth of a character by providing context and history. This online study explored how social robots narrating emotional backstories affect human empathy. Three backstories-happy, neutral (control), and sad- were crafted to mirror believable robot experiences. These narratives, personified as the robot's emotions, were conveyed through multi-modal video recordings of the robot that featured visual and textual elements. A within-subject experiment was conducted through a web-based survey among 60 English-speaking students from a German university. Our results highlight the significant role of backstories in shaping perceptions of robots, with the sad backstory notably increasing empathy towards social robots, diverging from prior Human-Robot Interaction paradigms. Furthermore, gender-based differences in empathetic responses highlighted the impact of sad narratives on female participants, with the robot's voice set as female. Open-ended feedback suggested the need for improved expressiveness in facial expressions and gaze strategies to mitigate the uncanny valley phenomenon.

Highly anthropomorphic robots risk triggering expectation mismatch that can lead to disappointment when robot behavior falls short. This study investigates how actively teaching a social humanoid robot to narrate a story influences user expectations, negative attitudes, anxiety, and perceptions of storytelling quality, compared to passive observation. University students (N=40) were assigned to either a teaching or non-teaching condition. Teaching participants instructed the robot using speech and gestures, while the non-teaching group observed the robot narrate the resulting storytelling video. Results showed that active teaching reduced expectation shifts, suggesting greater alignment between user beliefs and robot capability. However, robot-related anxiety increased in the teaching group, while the non-teaching group consistently reported higher negative attitudes. Storytelling quality was more strongly influenced by robot anthropomorphism in the non-teaching group. Participants who blamed the robot gave lower storytelling ratings, whereas those who blamed the AI model or programmer were more lenient. These findings highlight the importance of managing expectations through interactive teaching of robot tutee.

Understanding off-road environments, especially forests, is a challenging problem in computer vision due to factors including illumination, features extraction and ambiguity. This work aims at analysing the off-road environments by implementing Panoptic segmentation (PS) architecture taking into consideration the dynamic lighting conditions. To assist this, a novel off-road Panoptic dataset is also presented and consists of 285 annotated forestry images in varying illumination conditions. To handle the problem of illumination variations, Shadow-removal/exposure correction techniques are further experimented with. We include these correction techniques as a preprocessing step not only to improve the quality of feature extraction but also to reduce the ambiguity caused by varying lighting conditions. The experiments are further supported with qualitative and quantitative analysis. The source code and dataset is available at github.

Interpreting the results of Convolutional Neural Networks remains a challenging task. Quantitative evaluations apart from precision, recall, and their extensions are rare and usually do not cover the necessary aspects of specific applications. In this work, a methodology based on the intrinsic dimensionality of the image space and latent space in multiple layers is presented. This methodology has been used in other literature for classification but is leveraged to object detection where the interpretation of the results is more complex. The suitability of the intrinsic dimensionality is evaluated first for general augmentation techniques in multiple datasets and with multiple networks and later on a specific use case with multiple disturbances included. With the help of the intrinsic dimensionality, conclusions about the robustness can be drawn which are not apparent from the precision and the suitability of the methodology as an auxiliary quantifiable metric therefore shown.

Acquiring ground-truth data for crop mapping is a challenging task in developing countries. Limited resources, inconsistent agricultural practices across the country, and inadequate infrastructure at the administrative level pose a significant challenge in collecting dataset information. This study proposes an active labelling framework for automated ground truth data generation in areas with limited or no ground truth information available. Sentinel 2 images and vegetative indices are visually interpreted for the identification of Wheat and Rice fields. This hand-labelled data is incorporated into the framework as training data to generate crop maps at 10m resolution using light weight, ConvLSTM model. Testing is performed for two spatially distinct districts with different field sizes and crop distribution in Pakistan. The results are consistent with an accuracy of 77.8%, F1 score of 87.3% and IOU of 70.7% for Gujranwala and 76%, 82% and 70% for Sargodha, promising the applicability of the proposed approach to generate large-scale crop labels, thereby enhancing the efficiency of crop mapping efforts in developing countries

The presented study investigated the dressing style preference of human interlocutors for the social robot, ROBIN, in a university setting. Through an online questionnaire format, the research examined the impact of robot attire on human-robot interaction (HRI), and the perception of social robots in a social context. A mixed-methods approach was employed, conducting within-subjects empirical study via an online questionnaire that consisted of user demographics, social factors, constructs of robot usage, and two identical HRI videos. The videos featured ROBIN, a humanoid robot, dressed in formal vs. casual attire, respectively, as a representative from the student service center interacting with a human student. The findings indicated that 51.35% probable human interlocutors expressed a preference for the casual clothing style, while 48.65% preferred formal style. Additionally, participants associated social traits such as friendly, helpful, comfortable, approachable, and interesting with the robot’s casual attire. This study highlights the significance of robot clothing in personalized HRI, and its impact on perception of social robots by humans. Analyzing the interlocutor preferences for robot dressing style, it emphasizes clothing as an influential factor in the design of socially acceptable robots.

The application of autonomous vehicles becomes more and more essential. LiDAR sensors play a significant role in environmental perception. However, rain-, fog-, snow- or dust particles disturb the point clouds and affect LiDAR-based map reconstruction and object detection algorithms. Widely scattered particles can be filtered using statistics. In contrast, dense fog or dust clouds are more challenging to deal with as it is difficult to distinguish them based on their statistics from parts of the environment. Literature provides numerous examples of particle filter applications. Still, the applicability in challenging environments as the off-road domain remains unclear. Therefore, this paper reviews and tests state-of-the-art particle filters on-and off-road scenes.

In the following work object detection approaches with Convolutional Neural Networks (CNNs), which have provable characteristics regarding translational robustness, are proposed, evaluated in an application scenario, and compared to state of the art approaches. The provable characteristics are achieved by transferring theoretical results from wavelet theory and scattering networks to common CNNs used for classification. Therefore first a CNN is modeled as a scattering network. Needed parameters are estimated with data relevant for application scenarios. With the obtained information first the best feature extractor for a given application scenario is chosen. Afterward, the theory is extended to cover object detection networks. The proposed approaches are trained on simulated and real datasets and evaluated on real datasets.

Autonomous driving in a pedestrian zone is a challenging task. Technische Universitaet Kaiserslautern (TUK) is currently researching autonomous driving on the university campus for elderly or disabled people. This paper presents a novel campus dataset from the TUK campus, recorded over the span of one year for an autonomous bus project. John Deere’s Gator X855D is used for the work which is equipped with an inertial GPS navigation system, stereo cameras, monocular camera, and lidar sensors. For pedestrian safety during autonomous driving, the sensors are attached to capture the view of all four directions. Each sensor is calibrated with respect to the rear axle center of the vehicle and the intrinsic/extrinsic calibration values are provided. Moreover, the loop closure is performed in every data sequence. Several pose estimation and deep learning techniques are implemented to validate the provided data. The dataset is publicly available4.

Robust off-road perception for autonomous navigation is hard to achieve. Versatile environments, different hardware, and numerous disturbances limit the perceptional portability in changing applications and cross-platform. This contribution proposes sensor-fusion considering the data quality of uncertain sensors to increase the classification and mapping components’ perceptual robustness. The resulting benefits on perception are demonstrated using the autonomous off-road robot U5023.

In general, humanoid robots mostly use fixed-devices (e.g., camera or sensors) to detect human non-verbal communication, which have limitations in many real-life scenarios. Wearable devices could play an important role in many real-life scenarios. To address this, we propose using Myo armband for human-robot interaction using hand- and arm-based gestures. We present our end-to-end Spagti framework that is used first to train the user gestures using Myo armband and then to interact with a humanoid robot, called ROBIN, in real-time using space-free gestures.

This paper presents two variations of architecture referred to as RANet and BIRANet. The proposed architecture aims to use radar signal data along with RGB camera images to form a robust detection network that works efficiently, even in variable lighting and weather conditions such as rain, dust, fog, and others. First, radar information is fused in the feature extractor network. Second, radar points are used to generate guided anchors. Third, a method is proposed to improve region proposal network [1] targets. BIRANet yields 72.3/75.3% average AP/AR on the NuScenes [2] dataset, which is better than the performance of our base network Faster-RCNN with Feature pyramid network(FFPN) [3]. RANet gives 69/71.9% average AP/AR on the same dataset, which is reasonably acceptable performance. Also, both BIRANet and RANet are evaluated to be robust towards the noise.

The embedded system that is distributed within a bipedal robot is a key component of such a highly interwoven mechatronic system. Generally, it has to handle two competing main tasks – executing the embedded closed-loop control of the actuators and handling the communication with the higher-level control system. As the restrictions on physical size and energy consumption limit its computational resources, the design of the embedded nodes poses a potential bottleneck for the performance of the overall system. Hence, the following presents an approach to mitigate the conflicting requirements by deploying FPGA-based embedded nodes. It is illustrated how the additional flexibility at the logic level is used to implement the closed-loop force and impedance control of a series elastic actuator. Furthermore, it is shown how the consequent hardware/software co-design enables the deployment of a full featured robotic framework. To validate the concept, the properties of the implementation are characterized.

This paper describes a novel behavior-based local navigation approach for rough off-road scenarios. Trajectory candidates are generated based on vehicle kinematics and dynamics as well as the desired global trajectory. In contrast to on-road local navigation approaches, the work at hand proposes the use of a shiftable elevation grid map instead of occupancy maps since traversability in rough terrains does not only depend on location, but also on the robot's orientation. The traversability is evaluated by determining tire contact points with the terrain to take various different safety and efficiency aspects like underbody collisions and rollover risk into account. By exploiting the behavior-based control paradigm, the navigation approach can be easily extended and its robustness is shown in experimental evaluations using an Unimog U5023.

In this paper, an image-based segmentation method to improve autonomous robot navigation in the forest is presented. The detection is supported by a filtered image generated from a stereo-based pre-processing which is a byproduct of our obstacles detection system. To cope with the large variability of forest paths, the classifier is dynamically adapted to the current situation and the segmentation relies on different image features to ensure robustness against illumination changes. Furthermore, it is summarized how the detection results are transformed to the 3D space, using a plane which is extracted from the stereo data, to be stored and maintained in a probabilistic grid map.

A key capability of any indoor service robot is to explore arbitrary, unknown environments in order to record a complete and correct map in minimal time. Such a map is a prerequisite of common tasks like surveillance, transportation as well as search and rescue. In recent years a series of solutions has been proposed by the authors: a dynamic enhancement of the frontier-based approach, ground plan-based exploration and a hybrid combination of both. This paper evaluates the performance of each of these strategies within an everyday office scenario in simulation and reality and discusses their pros and cons.

Traversability analysis is an important aspect of autonomous navigation in robotics. In this paper, we relate the idea of traversability to safety and ease of road usage by defining a novel sensor-data driven metric called Road Traversability Index (RTI). The RTI translate the geometric interaction of vehicle with road into a distance modulated index that can be used as advice for a human driver or an autonomous agent intending to traverse a particular road segment using a specific vehicle. We present a framework in which 3D sensor data is converted into a road model, which in turn is converted into a roadmap based motion planning graph to represent the underlying configuration space. The RTI is defined as a function of the roadmap by axiomatically satisfying all required properties of road traversability. We have tested our algorithmic framework on simulated scenarios to explore safety; and real-world data sets to discover aspects of traversability for vehicles of various types. Experimental results show that RTI is a practical tool that reveals information that may be hidden to human inspection or other methods of assessment that do not explicitly model a vehicle.

It is a common goal to improve safety and performance of mobile indoor robots by predicting the movements of people in the surroundings. In contrast to many related works which exclusively employ sensors mounted on mobile robots, this work shows a method to achieve this goal in a smart environment where external sensors are used to sense people's positions. By using probabilistic models and filters, the evolution of the environment's state is predicted and optimal paths with respect to safety and performance are planned. Experiments in reality and in a simulation environment show the applicability in real-world scenarios and the advantages over classical path planning approaches.

Silt accumulation and sedimentation in canal beds leads to deterioration of watercourses over time. Every year a forced closure of the canals in the Indus basin is inevitable for canal cleaning, entailing a very large scale and costly operation. Silt removal precision is prone to inefficiencies due to subjective decision making in the cleaning process. In this paper, we lay out a theoretical framework to map the semi-structured (emptied) canal bed terrains with an Unmanned Aerial Vehicle (UAV) system for quantitative inspection of deposited silt. The study employs Gaussian process regression on sampled points to determine a continuous distribution of silt surface, thereby, predicting the volume of silt on canal bed. Our theoretical analysis builds upon certain mathematical bounds on the variance of estimated volume, while explicitly considering localization error and sensor noise. Essentially, we setup a framework for studying how tolerable are the process and measurement uncertainties, while achieving a desired accuracy in silt profile and corresponding volume. We demonstrate the regression results in simulations as well as lab-scaled-model (LMS151 laser scanner) with different sets of parameters. Volume estimation is verified practically and mathematical performance limits are proposed in established aerial canal inspection system.

The Bio-inspired Behavior-Based Bipedal Locomotion Control (B4LC) system consists of control units encapsulating feed-forward and feedback mechanisms, namely motor patterns and reflexes. To optimize the performance of motor patterns and reflexes in terms of stable locomotion on both even and uneven terrains, we present a learning scheme embedded in the B4LC system. By combining the Particle Swarm Optimization (PSO) method and the Expectation-maximization based Reinforcement Learning (EM-RL) method, a learning unit is comprised of an optimization module and a learning module embedded in the hierarchical control structure. The optimization module optimizes the motor patterns at hip and ankle joints with respect to energy consumption, stability and velocity control. The learning module generates compensating torques against disturbances at the ankle joints by combining the basis function derived from state information and the policy parameters. The optimization and learning procedures are conducted on a simulated robot with 21 DoFs. The simulation results show that the robot with optimized motor patterns and learned reflexes performs a more robust and stable locomotion on even and uneven terrains.

CREA robot is designed to climb up concrete walls. The robot uses the suction mechanism to provide adhesion and wheel mechanism for locomotion. Eleven chambers which are connected to one common reservoir are responsible to produce adhesion force. A controller is developed to independently control each chamber while satisfying certain criteria on the safety of the robot. It is also designed to reach minimum friction between active inflatable seals and wall. In conclusion, the controller is able to successfully meet the conditions of stability, minimum friction and safety.

Human shows remarkable skills in reactive balancing control on unknown disturbances while standing and walking. Though current bipedal robots can walk, run and step obstacles, they normally perform in a well-controlled environment. Unexpected perturbations can cause the tumbling of bipedal robots when they possess limited capability of rejecting disturbances. Studies upon neurology and psychophysics of human stance attempt to trace how the human deals with external disturbances. This paper introduces a methodology for disturbances estimation and compensation (DEC) for bipedal robot during standing. Previous psychophysical studies of human self-motion perception indicate that humans estimate and compensate disturbances as follows: firstly, multi-sensory inputs are fused to provide explicit measures and then the estimations of the external disturbances are performed based on them. Then, the estimations are fed into a local feedback control loop, compensating the disturbances. Thus, an approach of disturbance estimation and compensation is developed according to the psychophysical aspects of human. Various experiments, for instance, standing on a rotating plate with varying frequency and amplitudes and continuous external contact forces upon the torso of a bipedal robot, are implemented. Through analyzing and verifying the experimental results on a simulated biped, one can state that the DEC approach successfully serves the bipedal robot during perturbed stance.

In recent years, much effort has been made to provide services to an elderly person living alone at home. An essential component of facilitating the person is to identify his location in the home environment. Fundamentally, three different methods are being focused by the research community to address the issue of localizing the person. Most common approach is to install a variety of sensor systems in the home environment to track and monitor the person. Another variant includes developing wearable sensors that an elderly person carries with him all the time for being able to be tracked. A more recent approach, that is still under development, is to use an autonomous mobile robot in home environments to determine the location of the person. This paper attempts to summarize these efforts and provides directions for future research in finding the person in the home environment.

Simulation frameworks are wide-spread in the range of robotics to test algorithms and analyze system behavior beforehand – which tremendously reduces effort and time needed for conducting experiments on the real machines. This paper addresses a component based framework for simulating a wall-climbing robot that uses negative pressure adhesion in combination with an omnidirectional drive system. Key aspect is the adhesion system which interacts with the environmental features such as surface characteristics (e. g. roughness) or defects. An elaborate thermodynamic model provides the basis for a realistic simulation of the airflow between the virtual environment and the vacuum chambers of the robot. These features facilitate the validation of closed-loop controllers and control algorithms offline and in realtime. 1

This paper deals with the problem of assisting developers when verifying properties of complex behaviour-based systems. A central aspect of behaviour-based systems is the interaction between the behaviours, as a lot of the functionality of a system typically arises from this interaction. Hence, verification has to deal with the specialities of behaviour interaction. Previous work has introduced a concept for modelling behaviour-based systems as networks of finite-state automata and for applying model checking as verification technique. As the manual verification of large networks is tedious and errorprone, the work at hand introduces a concept for assisting developers by partly automating the verification process. The applicability of the presented approach is demonstrated using the behaviour-based control system of an autonomous bucket excavator.

Safe navigation on vertical concrete structures is still a great challenge for mobile climbing robots. The main problem is to find the optimum of applicability and safety since these systems have to fulfill certain tasks without endangering persons or their environment. This paper addresses aspects of safe navigation in the range of wall-climbing robots using negative pressure adhesion in combination with a drive system. In this context aspects of the developed robot control architecture will be presented and common hazards for this type of robots are examined. Based on this a risk prediction function is trained via methods of evolutionary algorithms using internal data generated inside of the behavior-based robot control network. Although there will always be a residual risk of a robot dropoff it is shown that the risk could be lowered tremendously by the developed analysis methods and counteractive measures.

In the range of robotics, simulation frameworks are very common. They are used to perform tests of algorithms, for optimization and to analyze the system behavior in situations, which would be hazardous or difficult for the real robot. This paper addresses a simulation framework related to a wall-climbing robot using negative pressure adhesion in combination with an omnidirectional drive system. The key aspect of this simulation is the adhesion system consisting of simulated pressure sensors, valves between adhesion chambers and vacuum reservoir and a simulated adaptive sealing proofing the vacuum chambers towards ambient air. The interaction of environmental features (e. g. surface characteristics like roughness or special geometries) and the vacuum chambers of the robot is handled by a thermodynamic model providing the basis for airflow simulation between the virtual surface and the robot. These features facilitate the validation of control algorithms and closed-loop controllers in realtime.

This work describes the combination of three software frameworks from two different domains: robotics and smart environments. The two robotic frameworks MCA2 and SimVis-3D that have been in use for several years on a multitude of different robotic systems and TinySEP, a modular framework for smart environments were combined to create a win-win-situation for both roboticists and ubiquitous computing researchers. The possibilities and advantages this combination can offer are discussed, especially in situations where mobile robots and smart environments coexist next to each other. This work is concluded by an experiment that shows the feasibility and the strengths of the proposed approach.

This paper focuses on the comparison of the low-level sensor failure detection capabilities of model-based Kalman filtering and a model-free Fuzzy voting approach. The ability to identify failing and degrading sensors is essential when dealing with error-prone data acquired in harsh application environments as can be typically found in the field of embedded systems. In order to investigate the respective performance concerning rejection of faulty data several experiments were conducted in a simulation environment. The two candidates were selected to gain more insight into the advantages and limitations of system modeling (or the lack thereof) in signal-level data fusion. The Kalman filter was selected as a typical candidate that relies on extensive models for both the system and information sources. The fuzzy approach, however, employs a heuristic that requires no modeling at all. This results in a broader field of possible applications since detailed knowledge is no longer required. Thus, it can be employed in scenarios that one would not be able to use a model-based algorithm. Such applications include scenarios with ongoing reconfiguration (e.g. wireless sensor networks) or systems with limited detail knowledge about the devices.

This paper presents a design concept and a exemplary realization of a perception system for naturally interacting humanoid robots. Relevant non-verbal interaction capabilities are selected based on psychological research. These interaction capabilities are transferred into a multi-functional user model which is exemplary implemented for interactive game scenarios. Benefits of this perception system design in comparison to existing realizations are a modular perception concept and the possibility to transfer psychological inter-personal research directly into human-robot interaction scenarios.

ABSTRACT In our societies, the number of senior citizens living on their own is increasing steadily. The lack of permanent attention results in the late detection of emergency situations. Labour‐intensive care is already a high burden for the society; therefore, it seems reasonable to promote technology that helps to detect and react in case of emergency situations that elderly people may encounter. In the last decade, assistive environments have been established by integrating surveillance devices into the living environments giving remote operators access to monitor the senior inhabitant at home for detecting emergency situations. However, due to poor privacy in terms of intrusion into the private life of an elderly person, there will be an unfavourably low acceptance of such systems. This paper introduces a two‐stage strategy and proposes to replace a possibly large number of human‐controlled monitoring devices by a single autonomous mobile system. The first stage will be performed by the autonomous system to detect an emergency situation. The human operator will be obligatory only at the final stage when the system assumes that an emergency has occurred and the final evaluation of the situation is required. The self‐assessment will reduce the human factor related to privacy issues. Copyright © 2011 John Wiley & Sons, Ltd.

The development of human-robot interaction sce-narios is a strongly situation-dependent as well as an extremely dynamic task. Humans interacting with the robot directly react on observed stimuli; changes in the environment are not avoid- able. Therefore it is impossible to test and verify interaction scenarios in real environments in a repeatable manner. In this paper, we propose a robot development framework that is able to simulate all required modules of the robot, its sensor system as well as its environment including persons. The simulation is able to represent all actuators of a humanoid robot like body, head and arm movements as well as facial expression. Besides the simulation of actuators all sensors are modeled directly in the framework. It is possible to integrate cameras, microphones, distance sensors, and RFI D tags and reader. These sensors provide the input for the robot control system based on the environmental situation including static elements like furniture and walls as well as movable objects like humans. The implementation of human movements is based on the H-Anim standard and a modeling tool which enables the user to record and integrate self-designed motions.

Introducing autonomous machines to construction areas can improve many of the occurring processes. Therefore, this paper deals with problems in the field of creating an autonomous bucket excavator. A novel behavior-based approach for motion control is presented which allows natural boom trajectories, achieves good environment disturbance compensation behavior, guarantees safety of the movements concerning human beings and structures, and keeps a high extensibility of the system for future improvements. Furthermore, a simulation of soil deals as the basis for safe tests of the excavator's behavior in a simulated dynamic environment.

Although recent statistics demonstrate a decrease in pedestrian fatalities, the absolute number of accident related deaths is sufficiently high to justify research in the area of vulnerable road user protection. Research has shown that situation awareness, which requires a significant amount of context information, is critical to timely intervention. Altered pedestrian behavior, due to traffic regulation, requires context information. For example, crosswalk presence and location knowledge can be of importance in pedestrian crossing scenarios. Therefore this paper discusses the implementation of a crosswalk detection algorithm, using Fourier transformation, augmented bipolarity, inverse perspective mapping template matching and edge orientation ratios for classification.

An audio system is one of the basic components of a humanoid robot designed for natural interaction.For many interaction purposes it is sufficient to use the sound detection and localization as attention system for the vision system.In this paper the audio perception module of the robot ROMAN is presented including the integration into the existing control structure and the localization algorithm using a microphone array with 6 microphones.The reduction of data into so called sector maps is presented and the interaction with the control architecture is shown.

In this paper the compliant low level control of a biologically inspired control architecture suited for bipedal dynamic walking robots is presented. It consists of elastic mechanics, a low-level compliant joint controller and a hierarchical reflex-based control layer. The former is implemented on a DSP while the reflex network is located on a desktop PC. Thus, one is able to utilize distribution as a powerful means to guarantee low latency and scalability. The concept is tested on a prototype leg mounted on a vertical slider that is designed to perform cyclic squat jumps. Thus, a suited mechatronic setup that features highly dynamic actuators as well as energy storage capabilities is derived. Cyclical jumping is employed as a benchmark for the system's performance. Experimental results of the prototype setup as well as simulation runs are presented and compared to human squat jumping.

A large-scale navigation system for autonomous off-road robots is presented which uses a topological map to navigate to a previously unseen target location. During path traversal, the system relies on a local navigation layer to avoid obstacles not modeled in the map. Data from this local layer is abstracted to learn both realistic topological edge cost measures and local traversability maps which allow more efficient route selection during topological exploration. On the topological level, a technique to handle impassable route segments in the map is presented and an exploration strategy that allows to discover new routes to the goal is introduced. The performance of the proposed concept is experimentally validated on the robot RAVON at the 2nd Military European Land Robot Trial 2008.

In this paper a combined action/perception-oriented approach for behavior-based robot software design is proposed. Action-oriented in that context denotes that the requirements for sensor information are directly derived from the navigational tasks on the control level. Perception-oriented design on the other hand determines further supporting behaviors from the data available. Taking into account the diversity of sensors and perception algorithms on the one hand and the need for a thorough control methodology on the other, the authors introduce a generic concept for sensor data abstraction through virtual sensors. Virtual sensors are standardized data representations which offer a clear interface for behavior-based robot control systems. The design method presented accounts for both, flexibility on the sensor processing layer and consistent structures on the control layer supporting reusability, extensibility, and traceability. Results documenting the applicability to complex robotic systems are shown in a case study about the off-road platform RAVON.

This paper presents a laser-based obstacle detection facility for off-road robotics in vegetated terrain. In the context of this work the mobile off-road platform RAVON was equipped with a 3D laser scanner and accompanying evaluation routines working on individual vertical scans. Identified terrain characteristics are used to build up a local representation of the environment. Introducing the abstraction concept of virtual sensors the transparent integration of additional terrain information on the basis of standardized behavior modules can be achieved.

For humanoid robots that should assist humans in their daily life the capability of an adequate interaction with human operators is a key feature. A key factor for human like interaction is the usage of non-verbal communication. Therefore robots must be able to have some kind of emotions. These emotions mainly depends on the achievement of the goals of the interaction. Psychologists point out that motives generate these kind of goals to humans. Because of this, this paper presents a motive model for the emotion-based architecture of the humanoid robot ROMAN. For the implementation of these motives a behavior-based approach is used. Furthermore some experiments concerning the functionality of the motives of interaction are presented and discussed.

Developers and end-users have to interface robotic systems for control and feedback. Such systems are typically co-engineered with their graphical user interfaces. In the past, a vast community of researchers has addressed issues of generality, deployment, usability, and re-usability of user interfaces. However, the support for creating graphical user interfaces in recent robotic frameworks is limited. In particular, there is typically no support for Web-based teleoperation. In this work, we propose a new Java-based editor with a plugin architecture for GUI elements and communication ports. Special focus is laid on platform-independent design, easy extensibility, connectivity to different robotic frameworks, usability and deployment. The tool offers convenient creation of graphical user interfaces and can publish them over the Web - making them accessible from any Java-enabled Web browser.

The design and implementing of a key point detector on embedded reconfigurable hardware is investigated. The major challenges are efficient hardware/software partitioning of the key point detector algorithm, data flow management as well as efficient use of memory, bus and processor. We present a modular and manual hardware/software co-design, with its implementation on a Xilinx XUP-Virtex II Pro board co-design to solve these issues.

The design and implementing of a key point detector on embedded reconfigurable hardware is investigated. The major challenges are efficient hardware/software partitioning of the key point detector algorithm, data flow management as well as efficient use of memory, bus and processor. We present a modular and manual hardware/software co-design, with its implementation on a Xilinx XUP-Virtex II Pro board to solve these issues.

The need for robust indoor localisation for all types of entities has been under continuous research by the ubiquitous community. Intelligent environments have to be supported with contextual information in order to facilitate intelligent behaviour. These contextual information include the location of humans and objects within the particular environment. Intelligent environments can be living areas with home automation, smart industrial plants, sensor-equipped office areas and indoor-emergency applications. So far technical solutions are either quite expensive or lack of precision for robust usage as components in intelligent service federations. We present rather low-cost localisation systems with great scalability based on active and passive RFID technology to locate humans, mobile service robots and objects of the daily use. The trade-off between technical effort and costs on the one hand and sufficient data accuracy for the application on the other hand is discussed. A motivation of our scenario, the technical concept and solution as well as the implementation and the integration that so far have been performed will be presented. Current prototypes of the proposed system are already being tested in a project aiming on development of smart assisted living environments.

Humanoid robots as assistance or educational robots is an important research topic in the field of robotics. Especially the communication of those robots with a human operator is a complex task since more than 60% of human communication is conducted non-verbally by using facial expressions and gestures. Although several humanoid robots have been designed it is unclear how a control architecture can be developed to realize a robot with the ability to interact with humans in a natural way. This paper therefore presents a behavior-based emotional control architecture for the humanoid robot head ROMAN. The architecture is based on 3 main parts: emotions, drives and actions which interact with each other to realize the human-like behavior of the robot. The communication with the environment is realized with the help of different sensors and actuators which will also be introduced in this paper.

For humanoid robots which are able to assist humans in their daily life, the capability for adequate interaction with human operators is a key feature. If one considers that more than 60% of human communication is conducted non-verbally (by using facial expressions and gestures), an important research topic is how interfaces for this non-verbal communication can be developed. To achieve this goal, several robotic heads have been designed. However, it remains unclear how exactly such a head should look like and what skills it should have to be able to interact properly with humans. This paper describes an approach that aims at answering some of these design choices. A behavior-based control to realize facial expressions which is a basic ability needed for interaction with humans is presented. Furthermore a poll in which the generated facial expressions should be detected is visualized. Additionally, the mechatronical design of the head and the accompanying neck joint are given

This paper presents a robust Kalman-based localization for outdoor vehicles. Outdoor vehicles require a fault-tolerant system that can manage temporary unavailable sensor measurements. The sensor system of the vehicle consists of odometry, inertial measurement unit (IMU) and differential global positioning system (DGPS) receiver. The system allows full 3D localization including position, attitude and velocities. Final experiments showed the localization and navigation capabilities of the outdoor robot RAVON

Many tasks examined for robotic application like rescue missions or humanitarian demining require a robotic vehicle to navigate in unstructured natural terrain. This paper introduces a motion control for a four-wheeled offroad vehicle trying to tackle the problems arising. These include rough ground, steep slopes, wheel slippage, skidding and others that are difficult to grasp with a physical model and often impossible to acquire with sensory equipment. Therefore, a more reactive approach is chosen using a behavior-based architecture. This way a certain generalization in unknown environment is expected. The resulting behavior network is described and experiments performed in a simulation environment as well as in real world are presented. Additionally the performance of the utilized vehicle in case of mechanical or electronic defects is examined in simulation.

This paper describes the thermodynamical model of a vacuum system for a climbing robot. Based on this model a simulation system is described, which is used to evaluate the influence of leakage situations on the adhesion system and to test control approaches. As a validation of the simulation parameters and the adhesion strategy a test platform was constructed and tested on concrete walls.

Locomotion of walking machines on a well defined path in unstructured terrain requires a model of the environment. But, in particular, middle sized robots like LAURON III don't provide the possibility to carry large or heavy sensors. This paper focuses on generating a 3D map of unstructured environment on the basis of sparse sensory information. In respect of walking robots this covers at first the selection of the next footsteps. For this purpose the advanced inference grid is introduced as a variant of the vector field histogram for the representation of the environment.

Presents methods and experiments of adaptive posture control for a four legged walking machine. Starting from the analysis of the implemented movement behaviour of BISAM we identify adequate tasks for adaptive control components and present adaptive posture control mechanisms for statically stable and dynamically stable movements. The reflex-based posture control is implemented via fuzzy control and reinforcement learning. The integration of the posture control in the control architecture is also described.

In this paper a multi-joint robot for sewer inspection tasks is presented. In order to increase the operating scope the robot has been designed to run round or over obstacles, to follow sewage branches and is operated with no wire attached to it. As a result of the wireless approach the robot has to carry an energy resource and must be abbe to act autonomously. In this paper we give a short description of the mechanical design and the electronic components used. Then we describe the control system and show sequences and results of in-pipe experiments.

Because of the very high workpiece costs in manufacturing processes, production errors should be detected online in order to avoid a series of defective workpieces. This article describes a qualitative evaluation method for time series that is applied to the diagnosis of a procedure for spraying car body parts. The determination of the parameters for the procedure is gained through learning data, which simplifies the industrial use enormously. A prototype that is already employed in production confirms the expected functionality of the procedure.

Service robots which should perform human-like operations will penetrate into a great number of applications in the future. Requirements for this is high flexibility, autonomy and the ability to adapt to new situations. The paper describes a design concept and a prototype implementation of an autonomous mobile humanoid service robot, which should mainly support people in their daily life as a personal or an assistance robot. The state of the research is that the general concept is developed and two anthropomorphic arms are built up. In the article the sensor system and the control architecture of the anthropomorphic robot are described. To evaluate the performance and motion abilities of the anthropomorphic arm the human arm kinematics and properties are discussed.

Presents an adaptive control architecture for the four legged walking machine BISAM. This architecture uses coupled neuro-oscillators as representation of periodic behaviours on different control levels such as joint movement, leg control and leg coordination. Coupled neuro-oscillators together with adaptive sensor based reflexes provide a robust and efficient representation for quadrupedal locomotion and support the use of online learning approaches to realize adaptation and optimization of locomotion behaviours.

In this paper a multijoint robot for sewer inspection tasks is presented. In order to increase the operating scope the robot has been made able to run round or over obstacles, to follow sewage branches and is aimed to work wirelessly unlike most other sewer inspection robots. As a result of the wireless approach the robot has to carry an energy resource and must be able to act autonomously. This article is focused on the mechanical design and the control hardware of the system. Additionally, we describe a first approach of a control strategy and some results of first tests.

Online learning of complex control behaviour of autonomous mobile robots is one of the current research topics. In this article a hybrid learning architecture based on self-organizing neural networks for online adaptivity is presented. The hybrid concept integrates different learning methods and task-oriented representations as well as available domain knowledge. The proposed concept is used for reinforcement learning of control strategies on different control levels on a walking machine.

In this paper a concept for a wheeled, multijoint robot able to operate in sewage systems is presented. The robot should work in an autonomous way. This concerns power supply, control and information processing. The cable-free navigation and the multijoint redundant construction of the robot enable higher mobility in sewage systems. In contrast to present systems, the robot should be able to avoid and overcome small obstacles, e.g socket displacements, holes or sediments, and to pass junctions and curves. In the following the results of a feasibility study are described in which the state of the art in sewer inspection robot as well as first experiments for the development of such a system is shown.

As presented in many papers neural networks are adequate for special control tasks because of their real-time processing capability, their fault-tolerance and their high adaptivity. The following paper aims to demonstrate how to build up a neural control architecture, consisting only of control algorithms based on neural networks. A further aspect is how to teach such control algorithms. As a testbed, a six-legged walking machine is selected. Due to the use of neural control architecture, the requirements to the hardware concept of the walking machine is described.>

In the following report the dynamic control of a robot leg is described. The control algorithm is trained using self-organizing feature maps. This approach belongs to the area of unsupervised learning techniques. The dynamic control is tested using a simulation system. Thereafter, it is used to control the physical robot leg.

The problem of correctly evaluating noisy and incorrect data for the interpretation of ultrasonic sensor signals is addressed. Neural networks, with their inherent characteristics of adaptivity and high fault and noise tolerance, are well suited for such tasks. A backpropagation algorithm is described for the control of the tracking behavior of an autonomous mobile robot. Input data are provided by three ultrasonic sensors mounted on the front of the vehicle. For more flexibility the behavior and learning capability of the tracking algorithm have been improved using different networks.>