Coordination schemes for distributed boundary coverage with a swarm of miniature robots

We provide a comparison of a series of original coordination mechanisms for the distributed boundary coverage problem with a swarm of miniature robots. Our analysis is based on real robot experimentation and models at different levels of abstraction. Distributed boundary coverage is an instance of the distributed coverage problem and has applications such as inspection of structures, de-mining, cleaning, and painting. Coverage is a particularly good example for the benefits of a multi-robot approach due to the potential for parallel task execution and additional robustness out of redundancy. The constraints imposed by a potential application, the autonomous inspection of a jet turbine engine, were our motivation for the algorithms considered in this thesis. Thus, there is particular emphasis on how algorithms perform under the influence of sensor and actuator noise, limited computational and communication capabilities, as well as on the policies about how to cope with such problems. The algorithms developed in this dissertation can be classified into reactive and deliberative algorithms, as well as non-collaborative and collaborative algorithms. The performance of these algorithms ranges from very low to very high, corresponding to highly redundant coverage to near-optimal partitioning of the environments, respectively. At the same time, requirements and assumptions on the robotic platform and the environment (from no communication to global communication, and from no localization to global localization) are incrementally raised. All the algorithms are robust to sensor and actuator noise and gracefully decay to the performance of a randomized algorithm as a function of an increased noise level and/or additional hardware constraints. Although the deliberative algorithms are fully deterministic, the actual performance is probabilistic due to inevitable sensor and actuator noise. For this reason, probabilistic models are used for predicting time to complete coverage and take into account sensor and actuator noise calibrated by using real hardware. For reactive systems with limited memory, the performance is captured using a compact representation based on rate equations that track the expected number of robots in a certain state. As the number of states explode for the deliberative algorithms that require a substantial use of memory, this approach becomes less tractable with the amount of deliberation performed, and we use Discrete Event System (DES) simulation in these cases. Our contribution to the domain of multi-robot systems is three-fold. First, we provide a methodology for system identification and optimal control of a robot swarm using probabilistic models. Second, we develop a series of algorithms for distributed coverage by a team of miniature robots that gracefully decay from a near-optimal performance to the performance of a randomized approach under the influence of sensor and actuator noise. Third, we design an implement a miniature inspection platform based on the miniature robot Alice with ZigBee ready communication capabilities and color vision on a foot-print smaller than 2 × 2 × 3 cm3.

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

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

Amanda Stella Markowska Prorok

EPFL2013

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

Plamen Prodanov

EPFL2006