A guiding robot aims to effectively bring people to and from specific places within environments that are possibly unknown to them. During this operation the robot should be able to detect and track the accompanied person, trying never to lose sight of her/him. A solution to minimize this event is to use an omnidirectional camera: its 360^∘ Field of View (FoV) guarantees that any framed object cannot leave the FoV if not occluded or very far from the sensor. However, the acquired panoramic videos introduce new challenges in perception tasks such as people detection and tracking, including the large size of the images to be processed, the distortion effects introduced by the cylindrical projection and the periodic nature of panoramic images. In this paper, we propose a set of targeted methods that allow to effectively adapt to panoramic videos a standard people detection and tracking pipeline originally designed for perspective cameras. Our methods have been implemented and tested inside a deep learning-based people detection and tracking framework with a commercial 360^∘ camera. Experiments performed on datasets specifically acquired for guiding robot applications and on a real service robot show the effectiveness of the proposed approach over other state-of-the-art systems. We release with this paper the acquired and annotated datasets and the open-source implementation of our method.
This paper deals with coordination in multi-agent systems based on Partially Observable Markov Decision Processes (POMDP). The well-known POMDP framework has been extended with consensus protocol, allowing for decentralized sharing of beliefs improving the local decision making of individual agents and eliminating the need to track the entire history of actions in the system to achieve coordination. To emphasize the importance of belief update after an observation is made in the system, we propose a novelty-biased consensus protocol. The efficiency of the proposed framework is demonstrated on the multi-agent system, which consists of three agents carrying out search missions in a simulation environment. The results obtained show that the mission completion time is significantly reduced without degradation in the success rate, while using simple POMDPs for individual agents.
We present an online and data-driven uncertainty quantification method to enable the development of safe human-robot collaboration applications. Safety and risk assessment of systems are strongly correlated with the accuracy of measurements: Distinctive parameters are often not directly accessible via known models and must therefore be measured. However, measurements generally suffer from uncertainties due to the limited performance of sensors, even unknown environmental disturbances, or humans. In this work, we quantify these measurement uncertainties by making use of conservation measures which are quantitative, system specific properties that are constant over time, space, or other state space dimensions. The key idea of our method lies in the immediate data evaluation of incoming data during run-time referring to conservation equations. In particular, we estimate violations of a-priori known, domain specific conservation properties and consider them as the consequence of measurement uncertainties. We validate our method on a use case in the context of human-robot collaboration, thereby highlighting the importance of our contribution for the successful development of safe robot systems under real-world conditions, e.g., in industrial environments. In addition, we show how obtained uncertainty values can be directly mapped on arbitrary safety limits (e.g, ISO 13849) which allows to monitor the compliance with safety standards during run-time.
In this paper we propose a resumable interruption framework for robotic applications which allows to "filter" misrecognition signals after their occurrence. Handling misrecognition is essential for deploying reactive systems into the real world, since being over-reactive to detection errors can lead to livelocks and stagnation. For example, constantly interrupting and resuming a picking task due to misrecognition can make the robot alternate between pre-grasping and grasping motions, without ever achieving the task. Our solution is based on resumable interruptions, continuing interrupted procedures from the exact preemption point if similar execution requests are received shortly after a cancellation order. This acts as a post-facto misrecognition filter, which stabilizes execution and ensures task completion. Compared with standard filtering, the post-facto approach allows to deliver signals faster and recover from misrecognition longer. The proposed system is verified through real robot experiments in dynamic and static environments.
Motion planning in the configuration space (C-space) induces benefits, such as smooth trajectories. It becomes more complex as the degrees of freedom (DOF) increase. This is due to the direct relation between the dimensionality of the search space and the DOF. Self-organizing neural networks (SONN) with their famous candidate, the Self-Organizing Map, have been proven to be useful tools for C-space reduction while preserving its underlying topology. In this work, the approach is adapted from human motion data towards robots’ kinematics. Furthermore, three additional models are implemented and compared to the existing ones with respect to their abilities to cover the used C-space of a robot and to preserve the topology. In total, the evaluation includes six SONN architectures, representing the consequent continuation of previous work. Generated Trajectories in the reduced SONN Output space were successfully tested in a robot simulation, providing a proof of concept for robot applications. The proposed method counteracts the Curse of Dimensionality for robots with many DOF, and thus a complete and optimal search algorithm can be used for path planning.
