Robots are networks of a variety of computing devices, such as powerful computing platforms but also tiny microcontrollers. The Robot Operating System (ROS) is the dominant framework for powerful computing devices. While ROS version 2 adds important features like quality of service and security, it cannot be directly applied to microcontrollers because of its large memory footprint. The micro-ROS project has ported the ROS 2 API to microcontrollers. However, the standard ROS 2 concepts are not enough for real-time performance: In the ROS 2 release “Foxy”, the standard ROS 2 Executor, which is the central component responsible for handling timers and incoming message data, is neither real-time capable nor deterministic. Domain-specific requirements of mobile robots, like sense-plan-act control loops, cannot be addressed with the standard ROS 2 Executor. In this paper, we present an advanced Executor for the ROS 2 C API which provides deterministic scheduling and supports domain-specific requirements. A proof-of-concept is demonstrated on a 32-bit microcontroller.

Bounding the end-to-end latency of processing chains in distributed real-time systems is a well-studied problem, relevant in multiple industrial fields, such as automotive systems and robotics. Nonetheless, to date, only little attention has been given to the study of the impact that specific frameworks and implementation choices have on real-time performance. This paper proposes a scheduling model and a response-time analysis for ROS 2 (specifically, version "Crystal Clemmys" released in December 2018), a popular framework for the rapid prototyping, development, and deployment of robotics applications with thousands of professional users around the world. The purpose of this paper is threefold. Firstly, it is aimed at providing to robotic engineers a practical analysis to bound the worst-case response times of their applications. Secondly, it shines a light on current ROS 2 implementation choices from a real-time perspective. Finally, it presents a realistic real-time scheduling model, which provides an opportunity for future impact on the robotics industry.

Mobile robots operating in a shared environment with pedestrians are required to move provably safe to avoid harming pedestrians. Current approaches like safety fields use conservative obstacle models for guaranteeing safety, which leads to degraded performance in populated environments. In this paper, we introduce an online verification approach that uses information about the current pedestrian velocities to compute possible occupancies based on a kinematic model of pedestrian motion. We demonstrate that our method reduces the need for stopping while retaining safety guarantees, and thus goals are reached between 1.4 and 3.5 times faster than the standard ROS navigation stack in the tested scenarios.

We consider the problem of learning from complex sequential demonstrations. We propose to analyze demonstrations in terms of the concurrent interaction phases which arise between pairs of involved bodies (hand-object and object-object). These interaction phases are the key to decompose a full demonstration into its atomic manipulation actions and to extract their respective consequences. In particular, one may assume that the goal of each interaction phase is to achieve specific geometric constraints between objects. This generalizes previous Learning from Demonstration approaches by considering not just the motion of the end-effector but also the relational properties of the objects' motion. We present a linear-chain Conditional Random Field model to detect the pair-wise interaction phases and extract the geometric constraints that are established in the environment, which represent a high-level task oriented description of the demonstrated manipulation. We test our system on single- and multi-agent demonstrations of assembly tasks, respectively of a wooden toolbox and a plastic chair.

Autonomous robots are highly relevant targets for interaction studies, but can exhibit behavioral variability that confounds experimental validity. Currently, testing on real systems is the only means to prevent this, but remains very labour-intensive and often happens too late. To improve this situation, we are working towards early testing by means of partial simulation, with automated assessment, and based upon continuous software integration to prevent regressions. We will introduce the concept and describe a proof-of-concept that demonstrates fast feedback and coherent experiment results across repeated trials.

The topic of motivation is a crucial issue for various human-robot interaction (HRI) scenarios. Interactional aspects of motivation can be studied in human-human interaction (HHI) and build the basis for modeling a robot's interactional conduct. Using an ethnographic approach we explored the factors relevant in the formation of motivation-relevant processes in an indoor-cycling activity. We propose an interactive, action-based motivation model for HRI that has been implemented in an autonomous robot system and tested during a long-term HRI study. The model is based on micro-analyses of human indoor cycling courses and resulted in an adaption of specific dialog patterns for HRI. A qualitative evaluation - accompanied by a quantitative analysis - demonstrated that the transfer of interaction patterns from HHI to HRI was successful with participants benefitting from the interaction experience (e.g., performance, subjective feeling of being motivated).

A key issue for interactive robots is smooth and natural motion. When robots are tele-operated, e.g. for tele-presence or during “Wizard of Oz” style studies, this requires an intuitive and responsive control interface. Furthermore, this interface should not interfere with perceiving the robot's sensors.

We present the design process, realization and evaluation of a robot system for nteractive object learning. The system-oriented evaluation, in particular, addresses an open problem for the evaluation of systems, where overall user satisfaction depends not only on the performance of the parts, but also on their combination, and on user behavior. Based on the PARADISE method known from spoken dialog systems, we have defined and applied internal and external metrics for fine-grained and largely automatable identification of such relationships. Through evaluation with n=28 subjects, indicator functions explaining up to 55% of variation in several satisfaction metrics were found. Furthermore, we demonstrate that the system's interaction style reduces the need for instruction and successfully recovers partial failures.

Movable cameras, or robotic eyes, have been of longstanding interest in robotics, but it remains challenging to achieve the various desirable characteristics (such as fast, small, robust, good-looking, etc.) at the same time. We consider robotic eyes targeted at interactive humanoid robots, and present a novel construction that provides human-level accelerations and velocities in a robust way, while its appearance avoids the uncanny valley effect by hiding all mechanics.

A robot's head is important both for directional sensors and, in human-directed robotics, as the single most visible interaction interface. However, designing a robot's head faces contradicting requirements when integrating powerful sensing with social expression. Furher, reactions of the general public show that current head designs often cause negative user reactions and distract from the functional capabilities. Therefore, this contribution presents a novel anthropomorphic robot head called "Flobi", which combines state-of-the-art sensing functionality with an exterior that elicits a sympathetic emotional response. It can display primary and secondary emotions in a human-like way, to enable intuitive human-robot-interaction. To facilitate further research on facial appearance, the exterior is fully modular and replaceable. While current state-of-the-art still requires trade-offs when integrating sensing and social expression, Flobi has been designed to enable service robotic applications, with high-resolution, wide-angle stereo vision, gyroscope motion compensation and stereo audio. For ease of integration, the head is self-contained, including 18 actuators, sensors and control boards, all in a human-head sized package.

If robots are to succeed in novel tasks, they must be able to learn from humans. To improve such human-robot interaction, a system is presented that provides dialog structure and engages the human in an exploratory teaching scenario. Thereby, we specifically target untrained users, who are supported by mixed-initiative interaction using verbal and non-verbal modalities. We present the principles of dialog structuring based on an object learning and manipulation scenario. System development is following an interactive evaluation approach and we will present both an extensible, event-based interaction architecture to realize mixed-initiative and evaluation results based on a video-study of the system. We show that users benefit from the provided dialog structure to result in predictable and successful human-robot interaction.