Abstract

Reasoning about objects in images and videos using 3D representations is re-emerging as a popular paradigm in computer vision. Specifically, in the context of scene understanding for roads, 3D vehicle detection and tracking from monocular videos still needs a lot of attention to enable practical applications. Current approaches leverage two kinds of information to deal with the vehicle detection and tracking problem: (1) 3D representations (eg. wireframe models or voxel based or CAD models) for diverse vehicle skeletal structures learnt from data, and (2) classifiers trained to detect vehicles or vehicle parts in single images built on top of a basic feature extraction step. In this paper, we propose to extend current approaches in two ways. First, we extend detection to a multiple view setting. We show that leveraging information given by feature or part detectors in multiple images can lead to more accurate detection results than single image detection. Secondly, we show that given multiple images of a vehicle, we can also leverage 3D information from the scene generated using a unique structure from motion algorithm. This helps us localize the vehicle in 3D, and constrain the parameters of optimization for fitting the 3D model to image data. We show results on the KITTI dataset, and demonstrate superior results compared with recent state-of-the-art methods, with upto 14.64 % improvement in localization error.

Abstract

Classical visual servoing approaches use visual features based on geometry of the object such as points, lines, region, etc. to attain the desired camera pose. However, geometrical features are not suited for visual servoing across different object instances due to large variations in appearance and shape. In this paper, we present a new framework for visual servoing across object instances. Our approach is based on a discriminative learning framework where the desired pose is estimated using previously seen examples. Specifically, we learn a binary classifier that separates the desired pose from all other poses for that object category. The classification error is then used to control the end-effector so that the desired pose is attained. We present controllers for linear, kernel and exemplar Support Vector Machine (SVM) and empirically discuss their performance in the visual servoing context. To address large intra-category variation in appearance, we propose a modified version of Histogram of Oriented Gradients (HOG) features for visual servoing. We show effective servoing across diverse instances over 3 object categories with zero terminal velocity and acceptable camera pose error at termination.

Abstract

Recently, quadcopters with their advance sensors and imaging capabilities have become an imperative part of the precision agriculture. In this work, we have described a framework which performs plantation monitoring and yield estimation using the supervised learning approach, while autonomously navigating through an inter-row path of the plantation. The proposed navigation framework assists the quadcopter to follow a sequence of collision-free GPS way points and has been integrated with ROS (Robot Operating System). The trajectory planning and control module of the navigation framework employ convex programming techniques to generate minimum time trajectory between way-points and produces appropriate control inputs for the quadcopter. A new `pomegranate dataset' comprising of plantation surveillance video and annotated frames capturing the varied stages of pomegranate growth along with the navigation framework are being delivered as a part of this work.

Abstract

Monocular SLAM refers to using a single camera to estimate robot ego motion while building a map of the environment. While Monocular SLAM is a well studied problem, automating Monocular SLAM by integrating it with trajectory planning frameworks is particularly challenging. This paper presents a novel formulation based on Reinforcement Learning (RL) that generates fail safe trajectories wherein the SLAM generated outputs do not deviate largely from their true values. Quintessentially, the RL framework successfully learns the otherwise complex relation between perceptual inputs and motor actions and uses this knowledge to generate trajectories that do not cause failure of SLAM. We show systematically in simulations how the quality of the SLAM dramatically improves when trajectories are computed using RL. Our method scales effectively across Monocular SLAM frameworks in both simulation and in real world experiments with a mobile robot.

Abstract

SPACE robots can be used to perform several onorbit tasks such as capturing space debris, servicing of satellites, and refueling. The proliferation of satellites as well as the growing interest in debris capture make it necessary to have robots that can perform these tasks autonomously [1]. The dynamics of robots in space differ from that of a grounded robot. The coupling of the arms and the base of a space robot creates reaction forces and moments on the base whenever the arms execute a maneuver, causing the base to rotate and translate in accordance with the laws of conservation of linear and angular momenta. However, it is generally desirable to keep the attitude of the base fixed relative to the sun and the Earth (or other bodies) for navigation and communication purposes, or to maintain the target in the field of view of the sensors. A change in celestial orientation may also result in loss of communication with the data relay satellite or the ground station. While attitude control using thrusters may be used, such operations consume fuel which is mainly reserved for orbital maneuvers. It has also been shown that manipulation without the use of attitude controllers is more robust [2]. The translation of the base however, does not pose signicant side eects [3]. Hence, researchers have focused on robotic manipulation with zero or minimal change in attitude, which is termed reactionless manipulation

Abstract

Field Programmable Gate Arrays (FPGA) exceed the computing power of software based implementations by breaking the paradigm of sequential execution and accomplishing more per clock cycle by enabling hardware level parallelization at an architectural level. Introducing parallel architectures for a computationally intensive algorithm like Rapidly Exploring Random Trees (RRT) will result in an exploration that is fast, dense and uniform. Through a cost function delineated in later sections, FPGA based combinatorial architecture delivers superlative speed-up but consumes very high power while hierarchical architecture delivers relatively lower speed-up with acceptable power consumption levels. To combine the qualities of both, a hybrid architecture, that encompasses both combinatorial and hierarchical architecture, is designed. To determine the number of RRT nodes to be allotted to the combinatorial and hierarchical blocks of the hybrid architecture, a cost function, comprised of fundamentally inversely related speed-up and power parameters, is formulated. This maximization of cost function, with its associated constraints, is then mathematically solved using a modified branch and bound, that leads to optimal allocation of RRT modules to both blocks. It is observed that this hybrid architecture delivers the highest performance-per-watt out of the three architectures for differential, quad-copter and fixed wing kinematics.

Abstract

In this paper, we present a framework for generating smooth and stable trajectories for wheeled mobile robots moving on uneven terrains. Instead of relying on static stability measures, the paper incorporates velocity and acceleration based constraints like no-slip and permanent wheel ground contact conditions in the planning framework. The paper solves this complicated problem in a computationally efficient manner with full 3D dynamics of the robot. The two major aspects of the proposed work are: Firstly, closed form functional relationships are derived which describes the 6 dof evolution of the robot’s state on an arbitrary 2.5D uneven terrain. This enables us to have a fast evaluation of robot’s dynamics along any candidate trajectory. Secondly, a novel concept of non-linear time scaling is introduced through which simple algebraic relations defining the bounds on velocities and accelerations are obtained. Moreover, non-linear time scaling also provides a new approach for manipulating velocities and accelerations along given geometric paths. It is thus exploited to obtain stable velocity and acceleration profiles. Extensive simulation results are presented to demonstrate the efficacy of the proposed methodology.

Abstract

Curb detection is a critical component of driver assistance and autonomous driving systems. In this paper, we present a discriminative approach to the problem of curb detection under diverse road conditions. We define curbs as the intersection of drivable and non-drivable area which are classified using dense Conditional random fields(CRF). In our method, we fuse output of a neural network used for pixel-wise semantic segmentation with depth and color information from stereo cameras. CRF fuses the output of a deep model and height information available in stereo data and provides improved segmentation. Further we introduce temporal smoothness using a weighted average of Segnet output and output from a probabilistic voxel grid as our unary potential. Finally, we show improvements over the current state of the art neural networks. Our proposed method shows accurate results over large range of variations in curb curvature and appearance, without the need of retraining the model for the specific dataset.

Abstract

Frontier detection is a critical component in autonomous exploration, wherein the robot decides the next best location to move in order to continue its mapping process. The existing frontier detection methods require dense reconstruction which is difficult to attain in a poorly textured indoor environment using a monocular camera. In this effort, we present an alternate method of detecting frontiers during the course of robot motion that circumvents the requirement of dense mapping. Based on the observation that frontiers typically occur around areas with sudden change in texture (zero-crossings), we propose a novel linear chain Conditional Random Field(CRF) formulation that is able to detect the presence or absence of frontier regions around such areas. We use cues like spread of 3D points and scene change around these areas as an observation to CRF. We demonstrate that this method gives us more relevant frontiers compared to other monocular camera based methods in the literature. Finally, we present results in an indoor environment, wherein frontiers are reliably detected around walls leading to new corridors, doors leading to new rooms or corridors and tables and other objects that open up to a new space in rooms.

Abstract

Recently, the interest in Micro Aerial Vehicles (MAVs) and their autonomous flights has increased tremendously and significant advances have been made. The monocular camera has turned out to be most popular sensing modality for MAVs as it is light-weight, does not consume more power, and encodes rich information about the environment around. In this paper, we present DeepFly, our framework for autonomous navigation of a quadcopter equipped with monocular camera. The navigable space detection and waypoint selection are fundamental components of autonomous navigation system. They have broader meaning than just detecting and avoiding immediate obstacles. Finding the navigable space emphasizes equally on avoiding obstacles and detecting ideal regions to move next to. The ideal region can be defined by two properties: 1) All the points in the region have approximately same high depth value and 2) The area covered by the points of the region in the disparity map is considerably large. The waypoints selected from these navigable spaces assure collision-free path which is safer than path obtained from other waypoint selection methods which do not consider neighboring information. In our approach, we obtain a dense disparity map by performing a translation maneuver. This disparity map is input to a deep neural network which predicts bounding boxes for multiple navigable regions. Our deep convolutional neural network with shortcut connections regresses variable number of outputs without any complex architectural add on. Our autonomous navigation approach has been successfully tested in both indoors and outdoors environment and in range of lighting conditions.