Whenever people move through their environments they do not move randomly. Instead, they usually follow specific trajectories or motion patterns corresponding to their intentions. Knowledge about such patterns enables a mobile robot to robustly keep track of persons in its environment and to improve its behavior. This paper proposes a technique for learning collections of trajectories that characterize typical motion patterns of persons. Data recorded with laser-range finders is clustered using the expectation maximization algorithm. Based on the result of the clustering process we derive a Hidden Markov Model (HMM) that is applied to estimate the current and future positions of persons based on sensory input. We also describe how to incorporate the probabilistic belief about the potential trajectories of persons into the path planning process. We present several experiments carried out in different environments with a mobile robot equipped with a laser range scanner and a camera system. The results demonstrate that our approach can reliably learn motion patterns of persons, can robustly estimate and predict positions of persons, and can be used to improve the navigation behavior of a mobile robot. 1

Behavior selection is typically a “built-in” feature of behavior-based architectures and hence not amenable to change. There are, however, circumstances where changing behavior selection strategies is useful and can lead to better performance. In this paper, we demonstrate that such dynamic changes of behavior selection mechanisms are beneficial in several circumstances. We first categorize existing behavior selection mechanisms along three dimensions and then discuss seven possible circumstances where dynamically switching among them can be beneficial. Using the agent architecture framework APOC, we show how instances of all (non-empty) categories can be captured and how additional architectural mechanisms can be added to allow for dynamic switching among them. In particular, we propose a generic architecture for dynamic behavior selection, which can integrate existing behavior selection mechanisms in a unified way. Based on this generic architecture, we then verify that dynamic behavior selection is beneficial in the seven cases by defining architectures for simulated and robotic agents and performing experiments with them. The quantitative and qualitative analyses of the results obtained from extensive simulation studies and experimental runs with robots verify the utility of the proposed mechanisms.

This paper proposes a new hierarchical formulation of POMDPs for autonomous robot navigation that can be solved in real-time, and is memory efficient. It will be referred to in this paper as the Robot Navigation–Hierarchical POMDP (RN-HPOMDP). The RN-HPOMDP is utilized as a unified framework for autonomous robot navigation in dynamic environments. As such, it is used for localization, planning and local obstacle avoidance. Hence, the RN-HPOMDP decides at each time step the actions the robot should execute, without the intervention of any other external module for obstacle avoidance or localization. Our approach employs state space and action space hierarchy, and can effectively model large environments at a fine resolution. Finally, the notion of the reference POMDP is introduced. The latter holds all the information regarding motion and sensor uncertainty, which makes the proposed hierarchical structure memory efficient and enables fast learning. The RN-HPOMDP has been experimentally validated in real dynamic environments.

The current paper presents techniques that facilitate mobile robots to be deployed as interactive agents in populated environments, such as museum exhibitions or trade shows. The mobile robots can be tele-operated over the Internet and this way provide remote access to distant users. Throughout this paper we describe several key techniques that have been developed in the relevant projects. They include robust mapping and localization, people-tracking and advanced visualizations for Web users. The developed robotic systems have been installed and operated in the premises of various sites. Use of the above techniques, as well as appropriate authoring tools, has resulted in drastic reduction in the installation times. Additionally, the systems were thoroughly tested and validated in real-world conditions. Such demonstrations ascertain the functionality and reliability of our methods and provide evidence as of the operation of the complete systems.

Abstract — We present a novel approach for determining robot movements that efficiently accomplish the robot’s tasks while not hindering the movements of people within the environment. Our approach models the goal-directed trajectories of pedestrians using maximum entropy inverse optimal control. The advantage of this modeling approach is the generality of its learned cost function to changes in the environment and to entirely different environments. We employ the predictions of this model of pedestrian trajectories in a novel incremental planner and quantitatively show the improvement in hindrancesensitive robot trajectory planning provided by our approach. I.

Abstract — A sensor-based model of a service robot’s environment is a prerequisite for interaction. Such a model should contain the positions of the robot’s interaction partners. Many reasonable applications require this knowledge in realtime. It could for example be used to realize efficient path planning for delivery tasks. Additionally to the actual positions of the partners it is important for the service robot to predict their possible future positions. In this paper we propose an extensible framework that combines different sensor modalities in a general real-time tracking system. Exemplarily, a tracking system is implemented that fuses tracking algorithms in laser range scans as well as in camera images by a particle filter. Furthermore, human trajectories are predicted by deducing them from learned motion patterns. The observed trajectories are generalized to trajectory patterns by a novel method which uses Self Organizing Maps. Those patterns are used to predict trajectories of the currently observed persons. Practical experiments show that multimodality increases the system’s robustness to incorrect measurements of single sensors. It is also demonstrated that a Self Organizing Map is suitable for learning and generalizing trajectories. Convenient predictions of future trajectories are presented which are deduced from these generalizations. I.

This paper introduces a methodology for avoiding obstacles by controlling the robot's velocity. Contemporary approaches to obstacle avoidance usually dictate a detour from the originally planned trajectory to its goal position. In our previous work, we presented a method for predicting the motion of obstacles, and how to make use of this prediction when planning the robot trajectory to its goal position. This is extended in the current paper by also using this prediction to decide if the robot should change its speed to avoid an obstacle more effectively. The robot can choose to move at three different speeds: slow, normal and fast. The robot movement is controlled by a Hierarchical Partially Observable Markov Decision Process (POMDP). The POMDP formulation is not altered to accommodate for the three different speeds, to avoid the increase of the size of the state space. Instead, a modified solution of POMDPs is used.

An approach to motion planning among moving obstacles is presented, whereby obstacles are modeled as intelligent decision-making agents. The decision-making processes of the obstacles are assumed to be similar to that of the mobile robot. A probabilistic extension to the velocity obstacle approach is used as a means for navigation and modeling uncertainty about the moving obstacles' decisions.

This paper presents techniques that facilitate mobile robots to be deployed as interactive agents in populated environments such as museum exhibitions or trade shows. The mobile robots can be tele-operated over the Internet and, this way, provide remote access to distant users. Throughout this paper we describe several key techniques that have been developed in this context. To support safe and reliable robot navigation, techniques for environment mapping, robot localization, obstacle detection and people-tracking have been developed. To support the interaction of both web and on-site visitors with the robot and its environment, appropriate software and hardware interfaces have been employed. By using advanced navigation capabilities and appropriate authoring tools, the time required for installing a robotic tour-guide in a museum or a trade fair has been drastically reduced. The developed robotic systems have been thoroughly tested and validated in the real-world conditions offered in the premises of various sites. Such demonstrations ascertain the functionality of the employed techniques, establish the reliability of the complete systems, and provide useful evidence regarding the acceptance of tele-operated robotic tour-guides by the broader public.

Abstract — A sensor-based model of a service robot’s environment is a prerequisite for interaction. Such a model should contain the positions of the robot‘s interaction partners. Additionally to the actual positions of the partners it is important for the service robot to predict their possible future positions. This knowledge could for example be used to realize efficient path planning for delivery tasks. In this paper we propose an extensible framework for systems, that combine different sensor modalities in a general tracking system. Furthermore, human trajectories are predicted by deducing them from learned motion patterns. Exemplarily, a tracking system is implemented that fuses tracking algorithms in laser range scans as well as in camera images by a particle filter. The observed trajectories are generalized to trajectory patterns by a novel method which uses self organizing maps. Those patterns are used to predict trajectories of the currently observed persons. Practical experiments show that multimodality increases the system‘s robustness to incorrect measurements of single sensors. It is also demonstrated that a self organizing map is suitable for learning and generalizing trajectories. Convenient predictions of future trajectories are presented which are deduced from these generalizations. I.