Efficient and reliable navigation in off-road environments poses a significant challenge for robotics, especially when factoring in the varying capabilities of robots across different terrains. To achieve this, the robot system’s traversability is usually estimated to plan traversable routes through an environment. This paper presents a new approach that utilizes Deep Multimodal Variational Autoencoders (DMVAEs) for estimating the traversability of different robots in complex offroad terrains. Our method utilizes DMVAEs to capture essential environmental information and robot properties, effectively modeling factors that influence robotic traversability. The key contribution of this research is a two-stage traversability estimation framework for various robots in diverse off-road conditions that integrates robot properties in addition to environmental information to predict the traversability for various robots in a single model. We validate our method through real-world experiments involving four ground robots navigating an alpine environment. Comparative evaluations against state-of-the-art traversability estimation methods demonstrate the superior accuracy and robustness of our approach. Additionally, we investigate the transfer of trained models to new robots, enhancing their traversability estimation and extending the applicability of our framework.

The field of robotics has shown significant advances in autonomous systems, particularly in robot navigation. Since the decisions made during navigation can be difficult for human operators to understand, research aims to provide explanations that improve human-robot interaction (HRI). However, generating and designing such explanations with the intention of improving robot-related human factors is still an ongoing research challenge. This paper addresses this challenge by investigating the impact of different explanation types on a set of human factors in the context of robot navigation. For this purpose, we conducted a user study that examined the impact of six different explanation types on commonly used human factors, including trust, satisfaction, situation awareness, likeability, understandability, and perceived usefulness. Additionally, the study provides indications of their general applicability for robot navigation explanations through creation of sum ranks across the observed human factor metrics. The results show that depending on the chosen explanation type, a significant impact on the measured factors can be observed. While constraint-based explanations are generally rated highly across all factors, apologetic explanations are not perceived well across all measured human factors. Our results provide insights into the impact of explanation types used for robot navigation scenarios on robot-related human factors, and also provide practical insights for designing explanations for robot navigation scenarios.

In the field of off-road navigation, where traditional maps often fall short, intuitive and efficient path planning is essential for autonomous off-road vehicles. Navigating in off-road terrain poses unique challenges, requiring innovative solutions for users to understand and trust path suggestions made by an autonomous system. In this paper, we explore the integration of Explainable AI into off-road navigation systems to better understand the complexity of off-road environments. Our research introduces a method tailored to generate contextual explanations for chosen paths using terrain features, environmental factors, and robot capabilities. By combining inverse optimization techniques with shortest path algorithms, our approach aims to answer the question "Why is path p*recommended over path p′, which was expected by the user?" These explanations aim to shed light on the process of a robot’s path planning task, focusing on elevation changes, terrain obstacles, and optimal path choices, thus improving the user’s understanding of the chosen paths. A short user study evaluating the provided explanations generated in different off-road environments validates the effectiveness of our explanation algorithm and shows that it contributes to understanding the planning process of off-road navigation systems.

There is an interest in and need for the use of semiautonomous robots in various fields, such as disaster response. Over the years, different techniques for semiautonomous control were developed, ranging from teleoperation guidance to different user interface designs for setting task constraints and goals interactively. Among those, affordance templates emerged as a recent method for users to efficiently provide robots with contextual information about object shapes, properties, and affordances. In many fields where direct teleoperation is common, affordance templates seem to be a promising candidate for improving performance and usability. However, despite the reports on the potential benefits of this technique in comparison to direct teleoperation, they are often qualitative or focus on tasks where teleoperation is particularly challenging. This can be a problem because task difficulty can influence different performance metrics and human factors, so results from studies that show large differences in task difficulty between interaction modes cannot be directly generalized to tasks with smaller or non-existent differences in difficulty. In this study, we aim to evaluate the effectiveness of affordance templates in the context of debris removal for disaster response, a task where direct teleoperation is a viable technique. We compared the two methods in a simulated setting through a user study involving 41 participants by measuring a) usability through questionnaires and b) performance on secondary tasks, an established measure of spare information processing capacity. The study results show that despite similar difficulty, users performed better on secondary tasks when using affordance template-based semiautonomy in this setting.

The outdoor navigation capabilities of ground robots have improved significantly in recent years, opening up new potential applications in a variety of settings. Cost-based representations of the environment are frequently used in the path planning domain to obtain an optimized path based on various objectives, such as traversal time or energy consumption. However, obtaining such cost representations is still cumbersome, particularly in outdoor settings with diverse terrain types and slope angles. In this paper, we address this problem by using a data-driven approach to develop a cost representation for various outdoor terrain types that supports two optimization objectives, namely energy consumption and traversal time. We train a supervised machine learning model whose inputs consists of extracted environment data along a path and whose outputs are the predicted energy consumption and traversal time. The model is based on a ResNet neural network architecture and trained using field-recorded data. The error of the proposed method on different types of terrain is within 11% of the ground truth data. To show that it performs and generalizes better than currently existing approaches on various types of terrain, a comparison to a baseline method is made.

Abstract Robot localization is a fundamental capability of all mobile robots. Because of uncertainties in acting and sensing, and environmental factors such as people flocking around robots, there is always the risk that a robot loses its localization. Very often behaviors of robots rely on a reliable position estimation. Thus, for dependability of robot systems it is of great interest for the system to know the state of its localization component. In this paper we present an approach that allows a robot to asses if the localization is still correct. The approach assumes that the underlying localization approach is based on a particle filter. We use deep learning to identify temporal patterns in the particles in the case of losing/lost localization. These patterns are then combined with weak classifiers from the particle set and sensor perception for boosted learning of a localization estimator. Through the extraction of features generated by neural networks and its usage for training strong classifiers, the robots localization accuracy can be estimated. The approach is evaluated in a simulated transport robot environment where a degraded localization is provoked by disturbances cased by dynamic obstacles. Results show that it is possible to monitor the robots localization accuracy using convolutional as well as recurrent neural networks. The additional boosting using Adaboost also yields an increase in training accuracy. Thus, this paper directly contributes to the verification of localization performance.

The aim of this paper is to provide a comprehensive overview of the MICCAI 2020 AutoImplant Challenge. The approaches and publications submitted and accepted within the challenge will be summarized and reported, highlighting common algorithmic trends and algorithmic diversity. Furthermore, the evaluation results will be presented, compared and discussed in regard to the challenge aim: seeking for low cost, fast and fully automated solutions for cranial implant design. Based on feedback from collaborating neurosurgeons, this paper concludes by stating open issues and post-challenge requirements for intra-operative use. The codes can be found at https://github.com/Jianningli/tmi.