Human-centered environments are rich with a wide variety of spatial relations between everyday objects. For autonomous robots to operate effectively in such environments, they should be able to reason about these relations and generalize them to objects with different shapes and sizes. For example, having learned to place a toy inside a basket, a robot should be able to generalize this concept using a spoon and a cup. This requires a robot to have the flexibility to learn arbitrary relations in a lifelong manner, making it challenging for an expert to pre-program it with sufficient knowledge to do so beforehand. In this paper, we address the problem of learning spatial relations by introducing a novel method from the perspective of distance metric learning. Our approach enables a robot to reason about the similarity between pairwise spatial relations, thereby enabling it to use its previous knowledge when presented with a new relation to imitate. We show how this makes it possible to learn arbitrary spatial relations from non-expert users using a small number of examples and in an interactive manner. Our extensive evaluation with real-world data demonstrates the effectiveness of our method in reasoning about a continuous spectrum of spatial relations and generalizing them to new objects.

In autonomous exploration tasks, robots usually rely on a SLAM system to build a map of the environment online and then use it for navigation purposes. Although there has been substantial progress in robustly building accurate maps, these systems cannot guarantee the consistency of the resulting environment model. In this paper, we address the problem of robustly guiding a robot back to its starting location after exploring an unknown environment-even if the mapping system fails to produce a consistent map. To tackle this problem, we propose a two-step procedure. First, we check if the current map is consistent using a statistical test. If the map is consistent, we navigate the robot back to its starting location using a standard navigation system. In case of an inconsistent map, however, we propose to rewind the trajectory from the current location to the start without relying on a map. We implemented the proposed system in ROS and showcase its effectiveness on an autonomous exploration robot in real underground and office environments.

In the last years, many researchers started to consider teach-and-repeat approaches for reliable autonomous navigation. The paradigm, in all its proposed forms, is deeply rooted in the idea that the robot should autonomously follow a route that has been demonstrated by a human during a teach phase. However, human demonstrations are often inefficient in terms of execution time or may cause premature wear of the robot components due to jittery behavior or strong accelerations. In this paper, we propose the concept of teach, optimize and repeat, which introduces a trajectory optimization step between the teach and repeat phases. To address this problem, we further propose LexTOR, a constrained trajectory optimization method for teach and repeat problems, where the constraints are defined according to user preferences. At its core, LexTOR optimizes both the execution time and the trajectory smoothness in a lexicographic sense. The experiments show that LexTOR is very effective, both qualitatively and quantitatively, in terms of execution time, smoothness, accuracy and bound satisfaction.

Over the years, proposals have been made to employ line segments to build 2D maps of indoor environments. One of the basic steps of these approaches is the matching between scans (or, more generally, sets) of line segments, which is usually addressed using variants of the Iterative Closest Line (ICL) paradigm. ICL is based on the idea of associating closest line segments belonging to the two scans and of reducing the distance between them. In this paper, we propose two algorithms that go beyond this approach by exploiting the mutual compatibility between associations of line segments. Experimental results show that our algorithms significantly outperform, in terms of matching accuracy, traditional algorithms based on ICL, at the cost of a slightly longer execution time.

Map consistency is an important requirement for applications in which mobile robots need to effectively perform autonomous navigation tasks. While recent SLAM techniques provide an increased robustness even in the context of bad initializations or data association outliers, the question of how to determine whether or not the resulting map is consistent is still an open problem. In this paper, we introduce a novel measure for map consistency. We compute this measure by taking into account the discrepancies in the sensor data and leverage it to address two important problems in SLAM. First, we derive a statistical test for assessing whether a map is consistent or not. Second, we employ it to automatically set the free parameter of dynamic covariance scaling, a robust SLAM back-end. We present an evaluation of our approach on over 50 maps sourced from 16 publicly available datasets and illustrate its capability for the inconsistency detection and the tuning of the parameter of the back-end.