Search

The problem of autonomous navigation of a ground vehicle in unstructured environments is both challenging and crucial for the deployment of this type of vehicle in real-world applications. Several well-established communities in robotics research deal with these scenarios such as search and rescue robotics, planetary exploration, and agricultural robotics. Perception plays a crucial role in this context, since it provides the necessary information to make the vehicle aware of its own status and its surrounding environment. We present a review on the recent contributions in the robotics literature adopting learning-based methods to solve the problem of environment perception and interpretation with the final aim of the autonomous context-aware navigation of ground vehicles in unstructured environments. To the best of our knowledge, this is the first work providing such a review in this context.

Being able to estimate the traversability of the area surrounding a mobile robot is a fundamental task in the design of a navigation algorithm. However, the task is often complex, since it requires evaluating distances from obstacles, type and slope of terrain, and dealing with non-obvious discontinuities in detected distances due to perspective. In this paper, we present an approach based on deep learning to estimate and anticipate the traversing score of different routes in the field of view of an on-board RGB camera. The backbone of the proposed model is based on a state-of-the-art deep segmentation model, which is fine-tuned on the task of predicting route traversability. We then enhance the model's capabilities by a) addressing domain shifts through gradient-reversal unsupervised adaptation, and b) accounting for the specific safety requirements of a mobile robot, by encouraging the model to err on the safe side, i.e., penalizing errors that would cause collisions with obstacles more than those that would cause the robot to stop in advance. Experimental results show that our approach is able to satisfactorily identify traversable areas and to generalize to unseen locations., Accepted at IROS 2020

Surveying with unmanned aerial vehicles flying close to the terrain is crucial for the collection of details that are not visible when flying at higher altitudes. This type of missions can be applied in several scenarios such as search and rescue, precision agriculture, and environmental monitoring, to name a few. We present a strategy for the generation of low-altitude trajectories for terrain following. The trajectory is generated taking into account the morphology of the area of interest, represented as a georeferenced Digital Surface Model (DSM), while ensuring a safe separation from any obstacle. The surface model of the scenario is created by using a UAV-based photogrammetry software, which processes the images acquired during a preliminary mission at high altitude. The solution was developed, tested, and verified both in simulation and in real scenarios with a multirotor equipped with low-cost sensing. The experimental results proved the validity of the generation of trajectories at altitudes lower than most of the works available in the literature. The images acquired during the low-altitude mission were processed to obtain a high-resolution reconstruction of the area as a representative application result.

In this paper, a strategy for the mission planning of a UAV swarm in 3-D environments is presented. The operating space is represented as a 3-D grid and the A* algorithm is used; paths are planned for each UAV towards any possible target and the optimal combination, in terms of reducing the path length for the whole swarm, is considered. Further features and algorithm enhancements have been developed for reducing computational time, improving planned trajectories, and for the automatic redistribution of targets. The intended application is the deployment of UAVs for landslide monitoring and search of people involved in catastrophic events.

This paper describes the approach employed to implement the autonomous landing of an Unmanned Aerial Vehicle (UAV) upon a moving ground vehicle. We consider an application scenario in which a target, made of a visual pattern, is mounted on the top of a ground vehicle which roams in an arena using a certain path and velocity; the UAV is asked to find the ground vehicle, by detecting the visual pattern, and then to track it in order to perform the approach and finalize the landing. To this aim, Computer Vision is adopted to perform both detection and tracking of the visual target; the algorithm used is based on the TLD (Tracking-Learning-Detection) approach, suitably integrated with an Hough Transform able to improve the precision of the identification of the 3D coordinates of the pattern. The output of the Computer Vision algorithm is then exploited by a Kalman filter which performs the estimation of the trajectory of the ground vehicle in order to let the UAV track, follow and approach it. The paper describes the software and hardware architecture of the overall application running on the UAV. The application described has been practically used with success in the context of the “Mohamed Bin Zayed” International Robotic Challenge (MBZIRC) which took place in March 2017 in Abu Dhabi.