In 3D object mapping, category-level priors enable efficient object reconstruction and canonical pose estimation, requiring only a single prior per semantic category (e.g., chair, book, laptop, etc.). DeepSDF has been used predominantly as a category-level shape prior, but it struggles to reconstruct sharp geometry and is computationally expensive. In contrast, NeRFs capture fine details but have yet to be effectively integrated with category-level priors in a real-time multi-object mapping framework. To bridge this gap, we introduce PRENOM, a Prior-based Efficient Neural Object Mapper that integrates category-level priors with object-level NeRFs to enhance reconstruction efficiency and enable canonical object pose estimation. PRENOM gets to know objects on a first-name basis by meta-learning on synthetic reconstruction tasks generated from open-source shape datasets. To account for object category variations, it employs a multi-objective genetic algorithm to optimize the NeRF architecture for each category, balancing reconstruction quality and training time. Additionally, prior-based probabilistic ray sampling directs sampling toward expected object regions, accelerating convergence and improving reconstruction quality under constrained resources. Experimental results highlight the ability of PRENOM to achieve high-quality reconstructions while maintaining computational feasibility. Specifically, comparisons with prior-free NeRF-based approaches on a synthetic dataset show a 21% lower Chamfer distance. Furthermore, evaluations against other approaches using shape priors on a noisy real-world dataset indicate a 13% improvement averaged across all reconstruction metrics, and comparable pose and size estimation accuracy, while being trained for 5× less time.Code available at: https://github.com/snt-arg/PRENOM

Recent works on SLAM extend their pose graphs with higher-level semantic concepts like Rooms exploiting relationships between them, to provide, not only a richer representation of the situation/environment but also to improve the accuracy of its estimation. Concretely, our previous work, Situational Graphs (S-Graphs+), a pioneer in jointly leveraging semantic relationships in the factor optimization process, relies on semantic entities such as Planes and Rooms, whose relationship is mathematically defined. Nevertheless, there is no unique approach to finding all the hidden patterns in lower-level factor-graphs that correspond to high-level concepts of different natures. It is currently tackled with ad-hoc algorithms, which limits its graph expressiveness.To overcome this limitation, in this work, we propose an algorithm based on Graph Neural Networks for learning high-level semantic-relational concepts that can be inferred from the low-level factor graph. Given a set of mapped Planes our algorithm is capable of inferring Room entities relating to the Planes. Additionally, to demonstrate the versatility of our method, our algorithm can infer an additional semantic-relational concept, i.e. Wall, and its relationship with its Planes. We validate our method in both simulated and real datasets demonstrating improved performance over two baseline approaches. Furthermore, we integrate our method into the S-Graphs+ algorithm providing improved pose and map accuracy compared to the baseline while further enhancing the scene representation.

This paper explores the potential of 5G new radio (NR) Time-of-Arrival (TOA) data for indoor drone localization under different scenarios and conditions when fused with inertial measurement unit (IMU) data. Our approach involves performing graph-based optimization to estimate the drone’s position and orientation from the multiple sensor measurements. Due to the lack of real-world data, we use Matlab 5G toolbox and QuaDRiGa (quasi-deterministic radio channel generator) channel simulator to generate TOA measurements for the EuRoC MAV indoor dataset that provides IMU readings and ground truths 6DoF poses of a flying drone. Hence, we create twelve sequences combining three predefined indoor scenarios setups of QuaDRiGa with 2 to 5 base station antennas. Therefore, experimental results demonstrate that, for a sufficient number of base stations and a high bandwidth 5G configuration, the pose graph optimization approach achieves accurate drone localization, with an average error of less than 15 cm on the overall trajectory. Furthermore, the adopted graph-based optimization algorithm is fast and can be easily implemented for onboard real-time pose tracking on a micro aerial vehicle (MAV).

In this paper, we propose a solution for legged robot localization using architectural plans. Our specific contributions towards this goal are several. Firstly, we develop a method for converting the plan of a building into what we denote as an architectural graph (A-Graph). When the robot starts moving in an environment, we assume it has no knowledge about it, and it estimates an online situational graph representation (S-Graph) of its surroundings. We develop a novel graph-to-graph matching method, in order to relate the S-Graph estimated online from the robot sensors and the A-Graph extracted from the building plans. Note the challenge in this, as the S-Graph may show a partial view of the full A-Graph, their nodes are heterogeneous and their reference frames are different. After the matching, both graphs are aligned and merged, resulting in what we denote as an informed Situational Graph (is-Graph), with which we achieve global robot localization and exploitation of prior knowledge from the building plans. Our experiments show that our pipeline shows a higher robustness and a significantly lower pose error than several LiDAR localization baselines. Paper Video: https://youtu.be/3Pv7y8aOsUY

Fiducial markers can encode rich information about the environment and aid Visual SLAM (VSLAM) approaches in reconstructing maps with practical semantic information. Current marker-based VSLAM approaches mainly utilize markers for improving feature detections in low-feature environments and/or incorporating loop closure constraints, generating only low-level geometric maps of the environment prone to inaccuracies in complex environments. To bridge this gap, this paper presents a VSLAM approach utilizing a monocular camera along with fiducial markers to generate hierarchical representations of the environment while improving the camera pose estimate. The proposed approach detects semantic entities from the surroundings, including walls, corridors, and rooms encoded within markers, and appropriately adds topological constraints among them. Experimental results on a real-world dataset collected with a robot demonstrate that the proposed approach outperforms a marker-based VSLAM baseline in terms of accuracy, given the addition of new constraints while creating enhanced map representations. Furthermore, it shows satisfactory results when comparing the reconstructed map quality to the one rebuilt using a LiDAR SLAM approach.

Execution control is a critical task of robot architectures which has a deep impact on the quality of the final system. In this study, we describe a general method for execution control, which is a part of the Aerostack software framework for aerial robotics, and present technical challenges for execution control and design decisions to develop the method. The proposed method has an original design combining a distributed approach for execution control of behaviors (such as situation checking and performance monitoring) and centralizes coordination to ensure consistency of the concurrent execution. We conduct experiments to evaluate the method. The experimental results show that the method is general and usable with acceptable development efforts to efficiently work on different types of aerial missions. The method is supported by standards based on a robot operating system (ROS) contributing to its general use, and an open-source project is integrated in the Aerostack framework. Therefore, its technical details are fully accessible to developers and freely available to be used in the development of new aerial robotic systems.

In this paper we propose a particle filter localization approach, based on stereo visual odometry (VO) and semantic information from indoor environments, for mini-aerial robots. The prediction stage of the particle filter is performed using the 3D pose of the aerial robot estimated by the stereo VO algorithm. This predicted 3D pose is updated using inertial as well as semantic measurements. The algorithm processes semantic measurements in two phases; firstly, a pre-trained deep learning (DL) based object detector is used for real time object detections in the RGB spectrum. Secondly, from the corresponding 3D point clouds of the detected objects, we segment their dominant horizontal plane and estimate their relative position, also augmenting a prior map with new detections. The augmented map is then used in order to obtain a drift free pose estimate of the aerial robot. We validate our approach in several real flight experiments where we compare it against ground truth and a state of the art visual SLAM approach.

Deep learning techniques for motion control have recently been qualitatively improved, since the successful application of Deep Q- Learning to the continuous action domain in Atari-like games. Based on these ideas, Deep Deterministic Policy Gradients (DDPG) algorithm was able to provide impressive results in continuous state and action domains, which are closely linked to most of the robotics-related tasks. In this paper, a vision-based autonomous multirotor landing maneuver on top of a moving platform is presented. The behaviour has been completely learned in simulation without prior human knowledge and by means of deep reinforcement learning techniques. Since the multirotor is controlled in attitude, no high level state estimation is required. The complete behaviour has been trained with continuous action and state spaces, and has provided proper results (landing at a maximum velocity of 2 m/s), Furthermore, it has been validated in a wide variety of conditions, for both simulated and real-flight scenarios, using a low-cost, lightweight and out-of-the-box consumer multirotor.

Navigation in unknown indoor environments with fast collision avoidance capabilities is an ongoing research topic. Traditional motion planning algorithms rely on precise maps of the environment, where re-adapting a generated path can be highly demanding in terms of computational cost. In this paper, we present a fast reactive navigation algorithm using Deep Reinforcement Learning applied to multi rotor aerial robots. Taking as input the 2D-laser range measurements and the relative position of the aerial robot with respect to the desired goal, the proposed algorithm is successfully trained in a Gazebo-based simulation scenario by adopting an artificial potential field formulation. A thorough evaluation of the trained agent has been carried out both in simulated and real indoor scenarios, showing the appropriate reactive navigation behavior of the agent in the presence of static and dynamic obstacles.