This paper exposes a new algorithm designed to enhance the real-time crop/weed instance segmentation. The approach combines a learning-based method for instance segmentation with a feature model-based image processing strategy that leverages the vegetation characteristics of crops. The proposed algorithm compensates for the shortcomings of each method performing independently. The image processing strategy achieves precise crop segmentation by generating finely refined masks; but may introduce errors in weed segmentation. Conversely, instance segmentation methods perform well in accurately identifying both crops and weeds, but can produce imperfect masks in the presence of inaccurate bounding boxes. The experiments are conducted in different evaluation campaigns including the ACRE international competition framework. The results demonstrate that integrating color feature segmentation with state-of-the-art instance segmentation methods improves overall segmentation accuracy, achieving up to 0.80 mAP for maize crops and 0.83 mAP for bean crops, while maintaining real-time computational efficiency.

The actual paper provides a detailed comparative study of two rotorcraft configurations in terms of their stability with time-delay in the control loop of the system. These configurations correspond to the tilt-rotor (fully-actuated) and fixed-rotor (underactuated) rotorcraft. Such analysis considers the coupling between translation (slow dynamics) and rotational (fast dynamics) motions as a delayed system. Thus, a set of stability charts are presented to illustrate the stability profile for each configuration. We have carried out numerical models that captures essential dynamics of such aerial robots.

Catadioptric cameras developed recently provide images with large field of view. Nevertheless, due to the use of mirrors, these images contain significant radial distortions that are necessary to handle when processing them. In this paper, we present the use of differential geometry for the construction of a hybrid structure tensor suited to the multicomponent catadioptric images. This structure tensor allows, at the same time, to take into account the geometry of the mirror and the information provided by the multidimensional nature of these images. Smoothing process and edge detection experiments illustrate the potential of our proposed approach and show higher quality of adaptive processing.

In this paper, we describe an approach to autonomous navigation using a state observer for sensor based control. In particular, we investigate the task of corridor following in the case of sensory failure (unreliable data) and/or loss of measurement. Our approach uses a virtual sensory frame to project laser rangefinder scans, and builds visual features (namely the position of the vanishing point and the orientation of the corridor median line) to be used in the control law. To insure a safe and smooth navigation even when those parameters cannot be extracted, we design a finite time state observer to estimate the visual features with the objective of maintaining an efficient control of the robot. Simulation and experimental tests validate the proposed approach.

This work is part of a global framework that aims to build a complete set of algorithms for autonomous robot exploration, navigation and map building using a sole omnidirectional camera. It focuses on topology extraction of navigable free spaces to yield autonomous robot exploration. The paper proposes a new algorithm, the Omnidirectional Delta Medial Axis (ODMA), with linear-time implementation to extract robust topology of the robot's local free space. It first introduces an adapted metric to cope with the deformations involved by the catadioptric sensor, and that is conformal with the ground 2D-metric. Then, it produces a pruned skeleton of the free space, inspired by the delta medial axis. Experimental results validate the approach for both skeleton precision and stability with respect to the robot position and free space topology.

Medial axes are known to be very sensitive to shape irregularities. In this paper, we develop a solution to compute a stable medial axis of noisy discrete shapes. It introduces a parameter up to which a deformation (noise) of the shape is considered irrelevant, and thus ignored in the discrete Euclidian Medial Axis computation. We show the linearity property of the proposed algorithm and compare it with two recent state of the art methods: The Gamma Integer Medial Axis and the Discrete Linear Lambda Medial Axis using a single pruning parameter. Based on Kimia's database (216 binary images), we present comparative experimental results with respect to skeletonization quality, noise sensitivity and computation time.

In this paper, we propose a robust and fast active contour based method to free space detection in omnidirectional images where the problem of falsely detected obstacles is solved. We define a new functional energy formulation including altitude estimation of keypoints extracted nearby the active contour modeling the free space. The free space, so extracted, could help the robot in real time navigation and environment exploration tasks. To validate the efficiency of the proposed approach, the paper shows comparative results achieved with a classical formulation and our formulation of active contour energies, using images acquired by a robot exploring unknown indoor and outdoor environments, with no prior knowledge of the shape or the extend of the free space.

This paper contributes to adapt parametric and geometric active contour methods in a new framework to handle real time free space extraction while taking advantage of the properties of omnivision. Both methods were formally and algorithmically adapted and improved. Some comparative results, achieved on unknown indoor and outdoor images, are presented to validate the efficiency of our two snake based approaches. We also show that active contours can be applied to make a robot navigate autonomously, only using real omni images, thanks to the extracted free space skeleton.

Omnidirectional catadioptric cameras offer a large field of view and a complete information about the world surrounding the robot. In this paper, we describe a method to perform a fast and robust extraction of the omnidirectional free space using active contour models. The extracted free space could help the robot in real time navigation and environment exploration tasks. The presented approach will be compared to classical active contour methods usually applied to object segmentation. Some comparative results achieved in indoor and outdoor environments are shown to validate the approach.

This paper provides a complexity study of the deterministic localization problem in robot networks using local and relative observations only. This is an important issue in collective and cooperative robotics where global positioning systems (GPS) are not available, and the basic premise is the localization ability of the group. We prove that given a set of relative observations made by the robots, the unique unambiguous pose estimation of the robot network in a deterministic way is an$N\!P$-hard problem. This means that no polynomial-time algorithm can deterministically solve the unique pose estimation problem based on relative observations unless$P=N\!P$. The consequence is that no guarantee can be provided, in a polynomial time, that the possibly estimated poses of the robots will correspond to the effective (actual) ones. The proof is based on complexity theory where we build appropriate polynomial-time reductions interrelating the multirobot localization problem to a well-known$N\!P$-complete problem (the partition problem). This$N\!P$-hardness result opens questions and perspectives for research into approximations to overcome its intractability.

This paper contributes to the problem of deterministic localization of robot networks using local and relative observations only. This is an important issue in collective and cooperative robotics where global positioning systems are not available, and the basic premise is the localization ability of the group. We prove that, giving a set of relative observations made by the robots, the unique non ambiguous pose estimation of the robot network in a deterministic way, is a NP-hard problem. This means that no polynomial-time algorithm can deterministically solve the unique pose estimation problem based on relative observations. The consequence is that no guaranty can be provided, in a polynomial time, that the possibly estimated poses of the robots, will correspond to the effective (actual) ones. The proof is based on complexity theory. We build appropriate polynomial-time reductions acting on the localization problem and leading to well known NP-hard problems. The paper gives some tracks to overcome this issue.

We consider distributed systems made of weak mobile robots, that is, mobile devices, equipped with sensors, that are anonymous , autonomous , disoriented , and oblivious . The Circle Formation Problem (CFP) consists of the design of a protocol insuring that, starting from an initial arbitrary configuration where no two robots are at the same position, all the robots eventually form a regular n-gon —the robots take place on the circumference of a circle C with equal spacing between any two adjacent robots on C . CFP is known to be unsolvable by arranging the robots evenly along the circumference of a circle C without leaving C —that is, starting from a configuration where the robots are on the boundary of C . We circumvent this impossibility result by designing a scheme based on concentric circles . This is the first scheme that deterministically solves CFP. We present our method with two different implementations working in the semi-synchronous system (SSM) for any number n ≥ 5 of robots.

The present study proposes an innovative approach to qualitative mobile robot's localization using the concept of integral invariant on omnidirectional images. They are invariant depending on the image transformations caused by the movements of the robot. Several methods have been suggested to construct such invariants but they often rely on hypotheses about the transformation group which do not hold any more when dealing with omnidirectional sensors. These sensors benefit from an increasing interest in mobile robotics because of their field of view but they require adaptations of classical methods. This paper presents a method based on group averaging to construct invariant features which could be used to recognize a place with this type of sensors.