Abstract

While the literature has been fairly dense in the areas of scene understanding and semantic labeling there have been few works that make use of motion cues to embellish semantic performance and vice versa. In this paper, we address the problem of semantic motion segmentation, and show how semantic and motion priors augments performance. We propose an algorithm that jointly infers the semantic class and motion labels of an object. Integrating semantic, geometric and optical flow based constraints into a dense CRF-model we infer both the object class as well as motion class, for each pixel. We found improvement in performance using a fully connected CRF as compared to a standard clique-based CRFs. For inference, we use a Mean Field approximation based algorithm. Our method outperforms recently proposed motion detection algorithms and also improves the semantic labeling compared to the state-of-the-art Automatic Labeling Environment algorithm on the challenging KITTI dataset especially for object classes such as pedestrians and cars that are critical to an outdoor robotic navigation scenario.

Abstract

For autonomous navigation in urban environments, the ability to detect road intersections in advance is crucial, especially in the absence of auxiliary geographic information. In this paper we investigate a 3D Point Cloud based solution for intersection recognition and road segment classification. We set up the intersection recognition problem as one of decoding a linear-chain Conditional Random Field (CRF). This allows us to encode temporal consistency relations between adjacent scans in our process, leading to a less error prone recognition algorithm. We quantify this claim experimentally. We first build a grid map of the point cloud, segmenting the region surrounding the robot into navigable and non-navigable regions. Then, based on our proposed beam model, we extract a descriptor of the scene. This we do as each scan is received from the robot. Based on the descriptor we build a linear chain-CRF. By decoding the CRF-chain we are able to recognize the type of road segment taken into consideration. With the proposed method, we are able to recognize Xjunctions, T-shaped intersections and standard non-branching road segments. We compare the CRF-based approach with a standard SVM based one and show performance gain due to the CRF formulation.

Abstract

The challenges in generating minimum time trajectory and control for generic quadrocopter flying through sophisticated and unknown environment are explored in this paper. The proposed method uses convex programming technique to optimize polynomial splines, which are numerically stable for high-order including large number of segments and easily formulated for efficient computation. Moreover, exploiting the differential flatness of system, these polynomial trajectories encode the dynamics and constraints of the vehicle and decouple them from trajectory planning. The framework is fast enough to be performed in real time and results in solution which is close to time optimal. As control inputs are computed from the generated trajectory in each update, they are applicable to achieve closed-loop control similar to model predictive controller.

Abstract

Here the prototype of an intelligent flash light is presented which helps for outdoor navigation by projecting a directional arrow that guides a user from one point to another. The torchlight can be used for navigating in new campuses, can be used as a tool for search and rescue and also can be used for trekking and biking. By directly projecting the associated meta data like name of the place, distance to target and the heading information the torch eliminates the overhead involved in reading a map and comparing it with the surroundings to further decipher the map. It is an intelligent-ubiquitous flash light which over comes the limitation imposed by limited screen size of a GPS cellphone, a GPS watch or a GPS navigating device used in a car.

Abstract

Here we present the design of a highly dexterous 48 dof robotic hand. This high dexterity was possible because of the unique design of joints based on magnetic sliding and spherical spheres. The hand is tendon driven and is portable. We believe this is the robotic hand with the highest degree of freedom till date. Dexterity in robotic hands is an important parameter towards the complexity of the tasks they can do. It has been a design challenge to build an anthropomorphic robotic hand that can completely replicate the human hand in terms of its motion, torque and form factor. Here we have looked at the problem from a design perspective and achieved a hand with degrees of freedom more than the human hand in itself.

Abstract

This paper presents an effective method of fusing appearance and geometric (homography) cues that provides for accurate and reliable floor segmentation in significantly difficult situations hitherto not demonstrated in literature. A robot equipped with a monocular camera is able to segment floors over extremely long indoor sequences, when illumination conditions contrast over a single view, when the floor and non floor regions are of same color, when the texture of floor varies over a single image, when features are lost while the robot rotates and in the presence of extremely low lying obstacles. This reliability stems from an organic blending of appearance and homography cues at various levels and most importantly through a Recursive Bayes Filter formalism. Herein the appearance and homography based error models are appropriately weighed to come up with the eventual class probability of a feature track. Equally important the paper presents ways to mitigate the problems posed by virtual plane. Virtual plane problem occurs when obstacles of very low height classified as belonging to the ground by homography. We show extensive experimental results portraying accurate and reliable segmentation in situations where virtual plane problem becomes prominent and also in other challenging situations mentioned earlier.

Abstract

A solution to the relative scale problem where reconstructed moving objects and the stationary world are represented in a unified common scale has proven equivalent to a conjecture. Motion reconstruction from a moving monocular camera is considered ill posed due to known problems of observability. We show for the first time several significant motion reconstruction of outdoor vehicles moving along non-holonomic curves and straight lines. The reconstructed motion is represented in the unified frame which also depicts the estimated camera trajectory and the reconstructed stationary world. This is possible due to our Multibody VSLAM framework with a novel solution for relative scale proposed in the current paper. Two solutions that compute the relative scale are proposed. The solutions provide for a unified representation within four views of reconstruction of the moving object and are thus immediate. In one, the solution for the scale is that which satisfies the planarity constraint of the object motion. The assumption of planar object motion while being generic enough is subject to stringent degenerate situations that are more widespread. To circumvent such degeneracies we assume that the object motion to be locally circular or linear and find the relative scale solution for such object motions. Precise reconstruction is achieved in synthetic data. The fidelity of reconstruction is further vindicated with reconstructions of moving cars and vehicles in uncontrolled outdoor scenes.

Abstract

This paper presents a simulation framework for evolution on uneven terrains for a wheeled mobile robot (WMR) such as a synchronous drive robot. The framework lends itself as a tool capable of solving various problems, such as forward kinematic-based evolution, inverse kinematic-based evolution, path planning and trajectory tracking. This framework becomes particularly useful when we understand that the evolution problem (and hence, the various associated problems based on evolution) is particularly challenging on uneven terrain. Specifically, it is entailed to bring in the contact constraints posed by the interaction of the wheel and the ground as well as the holonomic constraints as the problem is formulated in a Differential Algebraic Equation setting. The problem becomes all the more crucial as vehicles moving on uneven terrain are becoming the order of the day. Nonetheless, there has not been much literature that deals in length the various aspects that go into the framework. This paper elaborates on the various aspects of the framework, presents simulation results on uneven terrain, where the vehicle evolves without slipping, and also presents substantial quantitative analysis in regard to wheel slippage. The main contributions of this paper are the motion planning using forward kinematic framework and a new formulation of inverse kinematics for wheeled robots on uneven terrains.

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. A novel Globally Asynchronous-Locally Synchronous (GALS) architecture using hybrid parallel-pipelined design is being used for the implementation. FPGA offers highly parallel hardware architectures that are not possible on conventional high end processors or other embedded controllers. 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 with the objective of parallelizing the computation. The proposed two-tier GALS architecture based system with hybrid parallel-pipelined architectural design when realized on FPGA shows its efficiency in terms of power, resources and response time in comparison with a conventional GALS design. Due to the asynchronous design, a good amount of logic in the hardware becomes combinational logic and hence a significant reduction in the total resource utilization and power-delay product (PDP) in the proposed architecture is observed. This paper also shows the clear advantage of using the FPGA instead of a general purpose processor for robotic system design.

Abstract

We present an autonomous system for outdoor terrain (road) mapping using a robot equipped with viable low cost sensors (2D laser scanner, cameras, odometry, gyroscope and commercial GPS). The research work on outdoor navigation with known maps has matured well in past few years, but navigation and exploration of roads in an unknown area is still emerging. The presented system is an amalgamation of various computation modules running in parallel and interacting asynchronously with each other through message queues. The goal of the system is for a vehicle to explore and build a road network graph of a given area by autonomously navigating through all the connected roads in the area. The graph nodes contain topographic and semantic properties to allow reconstruction of the road network at a later stage for easier navigation.