We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up our model parameters and training data by multiple orders of magnitude, enabling us to explore the scaling properties in terms of dataset size, model parameters, and compute. We evaluate DriveGPT across different scales in a planning task, through both quantitative metrics and qualitative examples, including closed-loop driving in complex real-world scenarios. In a separate prediction task, DriveGPT outperforms state-of-the-art baselines and exhibits improved performance by pretraining on a large-scale dataset, further validating the benefits of data scaling.

Abstract Web is becoming rich in data. Some of the sources from where these data are originating includes Blogs, YouTube, Twitter, Emails, E‐commerce, Banking, sensors, and the Internet of Things. But these data are structured in a very poor fashion. The content of the web is becoming heterogeneous in nature both in terms of compendium and structure. It can be said that these data are human‐readable data but the main motive is to draw inferences from these data which is only possible if it can be made machine‐accessible. Clustering is considered an important task to organize these data and draw meaningful inferences from these data. In this paper, a clustering approach is proposed that can be applied to knowledge graphs and the possibility of applying Locality Sensitive Hashing is explored. Given the size of linked data, it is observed that this approach can be effective and scalable in comparison to other clustering approaches such as Hierarchical clustering, K‐Means clustering, and K‐Medoid clustering in discovering different communities that are defined by the link structure of the graph. The experimental results on different types of Linked Data sources justify the efficacy of the proposed model in terms of scalability and efficiency.

In this article, we aim to answer an important set of questions about the potential longitudinal effects of repeated sharing and privacy settings decisions over jointly managed content among users in a social network. We model user interactions through a repeated game in a network graph. We present a variation of the one-shot Ultimatum Game, wherein individuals interact with peers to make a decision on a piece of shared content. The outcome of this game is either success or failure, wherein success implies that a satisfactory decision for all parties is made and failure instead implies that the parties could not reach an agreement. Our proposed game is grounded in empirical data about individual decisions in repeated pairwise negotiations about jointly managed content in a social network. We consider both a “continuous” privacy model as well the “discrete” case of a model wherein privacy values are to be chosen among a fixed set of options. We formally demonstrate that over time, the system converges toward a “fair” state, wherein each individual’s preferences are accounted for. Our discrete model is validated by way of a user study, where participants are asked to propose privacy settings for own shared content from a small, discrete set of options.

Accurate metrical localization is one of the central challenges in mobile robotics. Many existing methods aim at localizing after building a map with the robot. In this paper, we present a novel approach that instead uses geo-tagged panoramas from the Google Street View as a source of global positioning. We model the problem of localization as a non-linear least squares estimation in two phases. The first estimates the 3D position of tracked feature points from short monocular camera sequences. The second computes the rigid body transformation between the Street View panoramas and the estimated points. The only input of this approach is a stream of monocular camera images and odometry estimates. We quantified the accuracy of the method by running the approach on a robotic platform in a parking lot by using visual fiducials as ground truth. Additionally, we applied the approach in the context of personal localization in a real urban scenario by using data from a Google Tango tablet.

Robot localization is one of the most important problems in robotics. Most of the existing approaches assume that the map of the environment is available beforehand and focus on accurate metrical localization. In this paper, we address the localization problem when the map of the environment is not present beforehand, and the robot relies on a hand-drawn map from a non-expert user. We addressed this problem by expressing the robot pose in the pixel coordinate and simultaneously estimate a local deformation of the hand-drawn map. Experiments show that we can successfully identify the room in which the robot is located in 80% of the tests.

Navigation in complex and unknown environments is a major challenge for blind people. The most popular, conventional navigation aids such as white canes and guide dogs, however, provide limited assistance in such settings as they are constrained to interpret the local environment only. At the same time, they can hardly be combined with a walker required by elderly people with walking disabilities. Technologies developed in the field of robotics have the potential to assist blind people in complex navigation tasks as they can provide information about obstacles and reason on both global and local environment models. The contribution of this paper is a smart walker that enables blind users to safely navigate. It includes an innovative vibro-tactile user interface and a controller that takes into account human characteristics based on a user study. The walker has been designed to deal with the fact that humans can only sense and interpret a limited number of commands and have a delayed response. Our experiments validate our claim that the technique outlined in this paper guides a user to the desired goal in less time and with shorter traveled distance compared to a standard robotic controller.

The problem of simultaneously localization a robot and modeling the environment is a prerequisite for several robotic applications and a large variety of solutions have been proposed allowing robots to build maps and use them for navigation. Also the geodetic community addressed large-scale mapping for centuries, computing maps which span across continents. These mapping processes had to deal with several challenges that are similar to those of the robotics community. In this paper, we explain two key geodetic mapping methods that we believe are relevant for robotics. We also aim at providing a geodetic perspective on current state-of-the-art SLAM methods and at identifying similarities between the solutions proposed by both communities. The central goal of this paper is to bring both fields close together and to enable future synergies.

Non-linear error minimization methods became widespread approaches for solving the simultaneous localization and mapping problem. If the initial guess is far away from the global minimum, converging to the correct solution and not to a local one can be challenging and sometimes even impossible. This paper presents an experimental analysis of dynamic covariance scaling, a recently proposed method for robust optimization of SLAM graphs, in the context of a poor initialization. Our evaluation shows that dynamic covariance scaling is able to mitigate the effects of poor initializations. In contrast to other methods that first aim at finding a good initial guess to seed the optimization, our method is more elegant because it does not require an additional method for initialization. Furthermore, it can robustly handle data association outliers. Experiments performed with real world and simulated datasets show that dynamic covariance scaling outperforms existing methods, both in the presence and absence of data association outliers.

Developing the perfect SLAM front-end that produces graphs which are free of outliers is generally impossible due to perceptual aliasing. Therefore, optimization back-ends need to be able to deal with outliers resulting from an imperfect front-end. In this paper, we introduce dynamic covariance scaling, a novel approach for effective optimization of constraint networks under the presence of outliers. The key idea is to use a robust function that generalizes classical gating and dynamically rejects outliers without compromising convergence speed. We implemented and thoroughly evaluated our method on publicly available datasets. Compared to recently published state-of-the-art methods, we obtain a substantial speed up without increasing the number of variables in the optimization process. Our method can be easily integrated in almost any SLAM back-end.

State of the art methods for state estimation and perception make use of least-squares optimization methods to perform efficient inference on noisy sensor data. Much of this efficiency is achieved by using sparse matrix factorization methods. The sparsity structure of the underlying matrix factorization which makes these optimization methods tractable is highly dependent on the choice of variable reordering; but there has been no systematic evaluation of reordering methods in the SLAM community. In this paper we evaluate the performance of various reordering techniques on benchmark SLAM data sets and provide definitive recommendations based on our results. We also compare these state of the art algorithms against our simple and easy to implement algorithm which achieves comparable performance. Finally, we provide empirical evidence that few gains remain with respect to variants of minimum degree ordering.