The e-puck, a Robot Designed for Education in Engineering

Mobile robots have the potential to become the ideal tool to teach a broad range of engineering disciplines. Indeed, mobile robots are getting increasingly complex and accessible. They embed elements from diverse ﬁelds such as mechanics, digital electronics, automatic control, signal processing, embedded programming, and energy management. Moreover, they are attractive for students which increases their motivation to learn. However, the requirements of an effective education tool bring new constraints to robotics. This article presents the e-puck robot design, which specifically targets engineering education at university level. Thanks to its particular design, the e-puck can be used in a large spectrum of teaching activities, not strictly related to robotics. Through a systematic evaluation by the students, we show that the e-puck ﬁts this purpose and is appreciated by 90 percent of a large sample of students.

Synthesis, modeling, and experimental validation of distributed robotic search

James Pugh

The work of this thesis centers around the research subject of distributed robotic search. Within the field of distributed robotic systems, a task of particular interest is attempting to locate one or more targets in a possibly unknown environment. While numerous studies have proposed and analyzed methods to accomplish this, there is currently a lack of a strong foundation of tools and techniques that can be used to facilitate the development and evaluation of different approaches to distributed robotic search. In this work, we aim to provide such a foundation through tools, methods, models, and analysis of experimentation. An often overlooked aspect of the distributed robotic research process is the development and analysis of tools and modules to be used with robotic systems. These may include plug-ins for realistic robotic simulators, software/hardware systems to track multiple mobile robots in real-time, extension boards for robotic platforms, and the robots themselves. Along with other tools developed and used for this work, we focus particularly on the development, characterization, and validation of a fast, accurate on-board system for relative positioning and communication between robots, a capability which is critical for effective distributed robotic search. Designing individual robot controllers to generate a specific group behavior is a difficult and often counter-intuitive process. A possible alternative to hand-crafting distributed search controllers is automatic synthesis using machine-learning techniques. We explore the effectiveness of using a noise-resistant version of the Particle Swarm Optimization algorithm to optimize the weights of an embedded Artificial Neural Network, allowing the robot to learn obstacle avoidance behavior (a common benchmark for robotic learning techniques); we find that this technique appears to offer superior performance as compared to the canonical approach of using Genetic Algorithms for this type of learning. A method for faster learning using distributed evaluation in a robot team is tested and is found to offer comparable performance using only a fraction of the original learning time. This technique can be used for fast, effective learning and adaptation in a distributed robotic system performing search. The process of designing and analyzing algorithms for distributed robotic systems can be greatly facilitated if models are available to describe the dynamics of the algorithm at an abstract level. Inspired by previous examples in the distributed robotic field, we work to design a model of robotic search that captures the system at different levels of abstraction, ranging from accurately recreating the details of individual robots to describing the entire system as an indivisible whole. To capture the entire search process, we model both the exploration phase, where robots cover an environment in an effort to detect traces of targets, and the localization phase, where robots use target emission sensing to navigate towards the target. The utility of our models is demonstrated by using them to develop an effective technique for the declaration phase of search, where robots decide that a target has been accurately localized and announce its position. In distributed robotics research, it is important that techniques developed with abstracted simulations and models are ultimately validated using real robotic platforms in order to verify their correctness. In that spirit, we run systematic sound search experiments using teams of up to ten real robots. These experiments utilize the tools developed throughout the research process, demonstrate the utility of our learning technique for fast search adaptation, and serve to validate our models of distributed robotic localization. In addition, they allow us to analyze and better understand the subtle dynamics of the search process, providing information which should be useful for any future work on distributed robotic search.

EPFL2008

Models and Algorithms for Ultra-Wideband Localization in Single- and Multi-Robot Systems

Amanda Stella Markowska Prorok

Location is a piece of information that empowers almost any type of application. In contrast to the outdoors, where global navigation satellite systems provide geo-spatial positioning, there are still millions of square meters of indoor space that are unaccounted for by location sensing technology. Moreover, predictions show that people’s activities are likely to shift more and more towards urban and indoor environments– the United Nations predict that by 2020, over 80% of the world’s population will live in cities. Meanwhile, indoor localization is a problem that is not simply solved: people, indoor furnishings, walls and building structures—in the eyes of a positioning sensor, these are all obstacles that create a very challenging environment. Many sensory modalities have difficulty in overcoming such harsh conditions when used alone. For this reason, and also because we aim for a portable, miniaturizable, cost-effective solution, with centimeter-level accuracy, we choose to solve the indoor localization problem with a hybrid approach that consists of two complementary components: ultra-wideband localization, and collaborative localization. In pursuit of the final, hybrid product, our research leads us to ask what benefits collaborative localization can provide to ultra-wideband localization—and vice versa. The road down this path includes diving into these orthogonal sub-domains of indoor localization to produce two independent localization solutions, before finally combining them to conclude our work. As for all systems that can be quantitatively examined, we recognize that the quality of our final product is defined by the rigor of our evaluation process. Thus, a core element of our work is the experimental setup, which we design in a modular fashion, and which we complexify incrementally according to the various stages of our studies. With the goal of implementing an evaluation system that is systematic, repeatable, and controllable, our approach is centered around the mobile robot. We harness this platform to emulate mobile targets, and track it in real-time with a highly reliable ground truth positioning system. Furthermore, we take advantage of the miniature size of our mobile platform, and include multiple entities to form a multi-robot system. This augmented setup then allows us to use the same experimental rigor to evaluate our collaborative localization strategies. Finally, we exploit the consistency of our experiments to perform cross-comparisons of the various results throughout the presented work. Ultra-wideband counts among the most interesting technologies for absolute indoor localization known to date. Owing to its fine delay resolution and its ability to penetrate through various materials, ultra-wideband provides a potentially high ranging accuracy, even in cluttered, non-line-of-sight environments. However, despite its desirable traits, the resolution of non-line-of-sight signals remains a hard problem. In other words, if a non-line-of-sight signal is not recognized as such, it leads to significant errors in the position estimate. Our work improves upon state-of-the-art by addressing the peculiarities of ultra-wideband signal propagation with models that capture the spatiality as well as the multimodal nature of the error statistics. Simultaneously, we take care to develop an underlying error model that is compact and that can be calibrated by means of efficient algorithms. In order to facilitate the usage of our multimodal error model, we use a localization algorithm that is based on particle filters. Our collaborative localization strategy distinguishes itself from prior work by emphasizing cost-efficiency, full decentralization, and scalability. The localization method is based on relative positioning and uses two quantities: relative range and relative bearing. We develop a relative robot detection model that integrates these measurements, and is embedded in our particle filter based localization framework. In addition to the robot detection model, we consider an algorithmic component, namely a reciprocal particle sampling routine, which is designed to facilitate the convergence of a robot’s position estimate. Finally, in order to reduce the complexity of our collaborative localization algorithm, and in order to reduce the amount of positioning data to be communicated between the robots, we develop a particle clustering method, which is used in conjunction with our robot detection model. The final stage of our research investigates the combined roles of collaborative localization and ultra-wideband localization. Numerous experiments are able to validate our overall localization strategy, and show that the performance can be significantly improved when using two complementary sensory modalities. Since the fusion of ultra-wideband positioning sensors with exteroceptive sensors has hardly been considered so far, our studies present pioneering work in this domain. Several insights indicate that collaboration—even if through noisy sensors—is a useful tool to reduce localization errors. In particular, we show that our collaboration strategy can provide the means to minimize the localization error, given that the collaborative design parameters are optimally tuned. Our final results show median localization errors below 10 cm in cluttered environments.

EPFL2013

Error handling in multimodal voice-enabled interfaces of tour-guide robots using graphical models

Plamen Prodanov

Mobile service robots are going to play an increasing role in the society of humans. Voice-enabled interaction with service robots becomes very important, if such robots are to be deployed in real-world environments and accepted by the vast majority of potential human users. The research presented in this thesis addresses the problem of speech recognition integration in an interactive voice-enabled interface of a service robot, in particular a tour-guide robot. The task of a tour-guide robot is to engage visitors to mass exhibitions (users) in dialogue providing the services it is designed for (e.g. exhibit presentations) within a limited time. In managing tour-guide dialogues, extracting the user goal (intention) for requesting a particular service at each dialogue state is the key issue. In mass exhibition conditions speech recognition errors are inevitable because of noisy speech and uncooperative users of robots with no prior experience in robotics. They can jeopardize the user goal identification. Wrongly identified user goals can lead to communication failures. Therefore, to reduce the risk of such failures, methods for detecting and compensating for communication failures in human-robot dialogue are needed. During the short-term interaction with visitors, the interpretation of the user goal at each dialogue state can be improved by combining speech recognition in the speech modality with information from other available robot modalities. The methods presented in this thesis exploit probabilistic models for fusing information from speech and auxiliary modalities of the robot for user goal identification and communication failure detection. To compensate for the detected communication failures we investigate multimodal methods for recovery from communication failures. To model the process of modality fusion, taking into account the uncertainties in the information extracted from each input modality during human-robot interaction, we use the probabilistic framework of Bayesian networks. Bayesian networks are graphical models that represent a joint probability function over a set of random variables. They are used to model the dependencies among variables associated with the user goals, modality related events (e.g. the event of user presence that is inferred from the laser scanner modality of the robot), and observed modality features providing evidence in favor of these modality events. Bayesian networks are used to calculate posterior probabilities over the possible user goals at each dialogue state. These probabilities serve as a base in deciding if the user goal is valid, i.e. if it can be mapped into a tour-guide service (e.g. exhibit presentation) or is undefined – signaling a possible communication failure. The Bayesian network can be also used to elicit probabilities over the modality events revealing information about the possible cause for a communication failure. Introducing new user goal aspects (e.g. new modality events and related features) that provide auxiliary information for detecting communication failures makes the design process cumbersome, calling for a systematic approach in the Bayesian network modelling. Generally, introducing new variables for user goal identification in the Bayesian networks can lead to complex and computationally expensive models. In order to make the design process more systematic and modular, we adapt principles from the theory of grounding in human communication. When people communicate, they resolve understanding problems in a collaborative joint effort of providing evidence of common shared knowledge (grounding). We use Bayesian network topologies, tailored to limited computational resources, to model a state-based grounding model fusing information from three different input modalities (laser, video and speech) to infer possible grounding states. These grounding states are associated with modality events showing if the user is present in range for communication, if the user is attending to the interaction, whether the speech modality is reliable, and if the user goal is valid. The state-based grounding model is used to compute probabilities that intermediary grounding states have been reached. This serves as a base for detecting if the the user has reached the final grounding state, or wether a repair dialogue sequence is needed. In the case of a repair dialogue sequence, the tour-guide robot can exploit the multiple available modalities along with speech. For example, if the user has failed to reach the grounding state related to her/his presence in range for communication, the robot can use its move modality to search and attract the attention of the visitors. In the case when speech recognition is detected to be unreliable, the robot can offer the alternative use of the buttons modality in the repair sequence. Given the probability of each grounding state, and the dialogue sequence that can be executed in the next dialogue state, a tour-guide robot has different preferences on the possible dialogue continuation. If the possible dialogue sequences at each dialogue state are defined as actions, the introduced principle of maximum expected utility (MEU) provides an explicit way of action selection, based on the action utility, given the evidence about the user goal at each dialogue state. Decision networks, constructed as graphical models based on Bayesian networks are proposed to perform MEU-based decisions, incorporating the utility of the actions to be chosen at each dialogue state by the tour-guide robot. These action utilities are defined taking into account the tour-guide task requirements. The proposed graphical models for user goal identification and dialogue error handling in human-robot dialogue are evaluated in experiments with multimodal data. These data were collected during the operation of the tour-guide robot RoboX at the Autonomous System Lab of EPFL and at the Swiss National Exhibition in 2002 (Expo.02). The evaluation experiments use component and system level metrics for technical (objective) and user-based (subjective) evaluation. On the component level, the technical evaluation is done by calculating accuracies, as objective measures of the performance of the grounding model, and the resulting performance of the user goal identification in dialogue. The benefit of the proposed error handling framework is demonstrated comparing the accuracy of a baseline interactive system, employing only speech recognition for user goal identification, and a system equipped with multimodal grounding models for error handling.

EPFL2006