End user development (EUD) is an emerging paradigm in human–robot interaction, involving end users both creating and maintaining robot programs themselves. Formal methods encompass a set of techniques that are useful to EUD, emphasizing the correctness of programs that are often created using natural, on-the-fly and sometimes even sloppy end-user input. These techniques include, for example, correct-by-construction synthesis of robot programs given incomplete developer input, automated repair of these applications and formal verification of these applications against sets of correctness criteria. Despite the increasing popularity of EUD and formal methods individually in robotics, there is no comprehensive review of how both have been successfully combined. The primary objective is thereby to review current practices for applying formal methods within robot EUD. To achieve this objective, the authors include adjacent areas of EUD research, such as natural language programming, and adjacent approaches to formal methods, such as automated planning. Recognizing that the integration of EUD and formal methods in robotics is still a nascent topic, the secondary objective is to identify opportunities for future research. This review thereby provides a primer on how to conduct further integration of formal methods in robot EUD.
Motion prediction, recently popularized under the term world models, refers to anticipating the future states of agents or the future evolution of a scene, which is rooted in human cognition to bridge perception and decision-making, enabling us to anticipate, adapt, and act within an everchanging world. It lies at the core of intelligent autonomous systems, such as robotics and self-driving cars, to safely operate in dynamic and human-robot-mixed environments, and also informs broader time-series challenges. With advances in methods, representations, and datasets, the field has seen rapid progress, reflected in rapidly updated benchmark performance. However, when state-of-the-art methods are deployed in the real world, they are often found to struggle to generalize to open-world settings and fall short of deployment standards. This reveals a gap between reality and benchmarks, which are often idealized or ill-posed, and fail to capture real-world complexity. To address the pressing need for problem settings that better reflect real-world challenges and guide future research, this paper focuses on revisiting the generalization and applicability of motion prediction models, with an emphasis on robotics, autonomous driving, and human motion applications. We first provide a comprehensive taxonomy of motion prediction methods, covering representations, modelling methods, application domains, and evaluation protocols. We then revisit two fundamental problems: 1) how to push motion prediction models to be deployable to realistic deployment standards, where motion prediction does not act in a vacuum, but functions as one module of closed-loop autonomy stacks – it takes input from the localization and perception, and informs downstream planning and control. 2) how to generalize motion prediction models from limited seen scenarios/datasets to the open-world settings. We conclude by highlighting crucial challenges and open problems for future research. By doing so, we aim to recalibrate the community’s efforts, fostering progress that is not only measurable but also meaningful for real-world applications. The project webpage corresponding to this paper can be found here Link to the website of Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectives
Continuous-time state estimation is gaining in popularity due to its abilities to provide smooth solutions, handle asynchronous sensors, and interpolate between data points. While there are two main paradigms, parametric (e.g., temporal basis functions, splines) and nonparametric (Gaussian processes), the latter has seen less adoption despite its technical advantages and relative ease of implementation. In this article, we seek to rectify this situation by providing a new simplified explanation of GP continuous-time estimation rooted in the language of factor graphs, which have become the de facto estimation paradigm in much of robotics. To simplify onboarding, we also provide three working examples implemented in the popular GTSAM estimation framework.
