Abstract

This paper presents a novel exploration strategy for coordinated exploration between unmanned ground vehicles (UGV) and micro-air vehicles (MAV). The exploration is modeled as an Integer Programming (IP) optimization problem and the allocation of the vehicles(agents) to frontier locations is modeled using binary variables. The formulation is also studied for distributed system, where agents are divided into multiple teams using graph partitioning. Optimization seamlessly integrates several practical constraints that arise in exploration between such heterogeneous agents and provides an elegant solution for assigning task to agents. We have also presented comparison with previous methods based on distance traversed and computational time to signify advantages of presented method. We also show practical realization of such an exploration where an UGV-MAV team efficiently builds a map of an indoor environment.

Abstract

Reactive Collision avoidance for non-holonomic robots is a challenging task because of the restrictions in the space of achievable velocities. The complexity increases further when multiple non-holonomic robots are operating in tight/cluttered spaces. The present paper presents a framework specially carved out for such situations. But at the same time can be easily appended with any existing collision avoidance framework. At the crux of the methodology is the concept of non-linear time scaling which allows robots to reactively accelerate/de-accelerate without altering the geometric path. The framework introduced is completely independent of the robot kinematics and dynamics. As such it can be applied to any ground or aerial robot. Through this concept the collision avoidance is framed as a problem of choosing appropriate scaling transformations. We present a “scaled” variant of the collision cone concept which automatically induces distributiveness among robots. The efficacy of the proposed work is demonstrated through simulations of both ground as well as UAVs.

Abstract

Detecting multiple planes in images is a challenging problem, but one with many applications. Recent work such as J-Linkage and Ordered Residual Kernels have focussed on developing a domain independent approach to detect multiple structures. These multiple structure detection methods are then used for estimating multiple homographies given feature matches between two images. Features participating in the multiple homographies detected, provide us the multiple scene planes. We show that these methods provide locally optimal results and fail to merge detected planar patches to the true scene planes. These methods use only residues obtained on applying homography of one plane to another as cue for merging. In this paper, we develop additional cues such as local consistency of planes, local normals, texture etc. to perform better classification and merging. We formulate the classification as an MRF problem and use TRWS message passing algorithm to solve non metric energy terms and complex sparse graph structure. We show results on challenging dataset common in robotics navigation scenarios where our method shows accuracy of more than 85 percent on average while being close or same as the actual number of scene planes.

Abstract

Motion segmentation is an inevitable component for mobile robotic systems such as the case with robots performing SLAM and collision avoidance in dynamic worlds. This paper proposes an incremental motion segmentation system that efficiently segments multiple moving objects and simultaneously build the map of the environment using visual SLAM modules. Multiple cues based on optical flow and two view geometry are integrated to achieve this segmentation. A dense optical flow algorithm is used for dense tracking of features. Motion potentials based on geometry are computed for each of these dense tracks. These geometric potentials along with the optical flow potentials are used to form a graph like structure. A graph based segmentation algorithm then clusters together nodes of similar potentials to form the eventual motion segments. Experimental results of high quality segmentation on different publicly available datasets demonstrate the effectiveness of our method.

Abstract

In this paper we propose a framework for optimum steering input determination of all-wheel steer vehicles (AWSV) on rough terrains. The framework computes the steering input which minimizes the tracking error for a given trajectory. Unlike previous methodologies of computing steering inputs of car-like vehicles, the proposed methodology depends explicitly on the vehicle dynamics and can be extended to vehicle having arbitrary number of steering inputs. A fully generic framework has been used to derive the vehicle dynamics and a non-linear programming based constrained optimization approach has been used to compute the steering input considering the instantaneous vehicle dynamics, no-slip and contact constraints of the vehicle. All Wheel steer Vehicles have a special parallel steering ability where the instantaneous centre of rotation (ICR) is at infinity. The proposed framework automatically enables the vehicle to choose between parallel steer and normal operation depending on the error with respect to the desired trajectory. The efficacy of the proposed framework is proved by extensive uneven terrain simulations, for trajectories with continuous or discontinuous velocity profile.

Abstract

In this paper, we automate the traditional problem of Simultaneous Localization and Mapping (SLAM) by interleaving planning for exploring unknown environments by a mobile robot. We denote such planned SLAM systems as SPLAM (Simultaneous Planning Localization and Mapping). The main aim of SPLAM is to plan paths for the SLAM process such that the robot and map uncertainty upon execution of the path remains minimum and tractable. The planning is interleaved with SLAM and hence the terminology SPLAM. While typical SPLAM routines find paths when the robot traverses amidst known regions of the constructed map, herein we use the SPLAM formulation for an exploration like situation. Exploration is carried out through a frontier based approach where we identify multiple frontiers in the known map. Using Randomized Planning techniques we calculate various possible trajectories to all the known frontiers. We introduce a novel strategy for selecting frontiers which mimics Fast SLAM, selects a trajectory for robot motion that will minimize the map and robot state covariance. By using a Fast SLAM like approach for selecting frontiers we are able to decouple the robot and landmark covariance resulting in a faster selection of next best location, while maintaining the same kind of robustness of an EKF based SPLAM framework. We then compare our results with Shortest Path Algorithm and EKF based Planning. We show significant reduction in covariance when compared with shortest frontier first approach, while the uncertainties are comparable to EKF-SPLAM albeit at much faster planning times.

Abstract

Exploration is a core and important robotics area, whose applications include search and rescue robotics, planetary exploration etc. We know that this exploration task is best performed when using a multi-robot system. In this paper, we present an algorithm for multi-robot exploration of an unknown environment, taking into account the communication constraints between the robots. The aim of the robots is to explore the whole map as a pack, without losing communication throughout. The key task for us here is to allocate the target points for multiple robots so as to maximize the area explored and minimize the time and plan paths for the robots in such a way so as to avoid obstacles. A multi-robot exploration methodology is introduced similar to depth first strategy, that samples frontier points based on a metric function. This function aims to maximize the visibility gain or information gain while minimizing the distance to be travelled to the frontier points, such that the robots are within the limited communication distance of each other. The algorithm has been tested through simulation runs of various maps and results and evaluations have been presented based on it. The results effectively demonstrate that our algorithm allows robot pack to quickly accomplish the task of exploration and without the constraint ever breaking down. Here, we also present a comparative analysis of our algorithm with another exploration approach, which finds new areas based on population generation and utility calculation over the population. The results show tangible performance gain of this method over previous methods reported on exploration with limited communication constraints.

Abstract

In this paper we address the problem of detecting road intersections. We present two approaches to solve the problem of intersection detection in an unstructured outdoor setting. The first is a natural extension of the popular VFH* obstacle avoidance algorithm. It detects intersections and tracks, over a period of time, the angles at which gaps in the robot's certainty grid (CG) are first observed. The second approach uses techniques from image processing and computational geometry on the certainty grid image, to extract a skeleton of the navigable region, thus providing the intersections. We show experimental results portraying intersection detection due to both methods and show the results. On the whole, we found that the robot was able to detect all possible intersections.

Abstract

In this paper we introduce a novel framework of generating trajectories which explicitly satisfies the stability constraints such as no-slip and permanent ground contact on uneven terrain. The main contributions of this paper are: (1) It derives analytical functions depicting the evolution of the vehicle on uneven terrain. These functional descriptions enable us to have a fast evaluation of possible vehicle stability along various directions on the terrain and this information is used to control the shape of the trajectory. (2) It introduces a novel paradigm wherein non-linear time scaling brought about by parametrized exponential functions are used to modify the velocity and acceleration profile of the vehicle so that these satisfy the no-slip and contact constraints. We show that nonlinear time scaling manipulates velocity and acceleration profile in a versatile manner and consequently has exceptional utility not only in uneven terrain navigation but also in general in any problem where it is required to change the velocity of the robot while keeping the path unchanged like collision avoidance.

Abstract

This paper presents a Field Programmable Gate Array (FPGA) based implementation of Acceleration Velocity Obstacle based Collision Avoidance for an omni-directional robot with acceleration constraint. Specifically a parallel architecture for collision avoidance is proposed that portrays the advantages of FPGA implementation over the sequential implementation for same processor or clock speed. FPGA based robotics is seen to gain popularity due to low cost, portability, seamless interface to hardware and most importantly due to inherent parallelism enshrined in various robotic algorithms. FPGA realization of the algorithm in a simulation test bed vindicates its efficacy and comparison with sequential implementation is also highlighted. The paper proposes three different architectures for the implementation of the proposed algorithm viz. sequential architecture; a resource constrained pipelined architecture and a hybrid pipeline parallel architecture. The performances of those three architectures have been evaluated.