Abstract

Traditional visual servoing is able to navigate a robotic system between two views of the same object. However, it is not designed to servo between views of different objects. In this paper, we consider a novel problem of servoing any instance (exemplar) of an object category to a desired pose (view) and propose a strategy to accomplish the task. We use features that semantically encode the locations of object parts and define the servoing error as the difference between positions of corresponding parts in the image space. Our controller is based on the linear combination of 3D models, such that the resulting model interpolates between the given and desired instances. We conducted our experiments on five different object categories in simulation framework and show that our approach achieves the desired pose with smooth trajectory. Furthermore, we show the performance gain achieved by using a linear …

Abstract

We propose a novel collision avoidance formulation in the intent space, suitable for navigation of non-holonomic robots in human centered environments. The intent space is characterized by various bands of trajectories wherein each band can be thought to be a representation of a possible human intended motion and the uncertainty associated with it. We ascribe probabilities to human intentions and characterize the uncertainty around it through Gaussian state transition and its concomitant Gaussian parametric distribution. Given an intent space we design avoidance maneuvers based on our recent works on time scaled collision cone concept which provides analytical characterization of collision free velocities in dynamic environments. In this paper, we present a probabilistic variant of the time scaled collision cone which allows us to relate space of collision free velocities to an associated confidence measure. We also develop an optimization framework which extract such specific solutions from the entire solution space that achieves an elegant balance between the objective of minimizing risk and ease of avoidance maneuver. We further show that by accounting for possible intents in human motion, the method transcends the realm of reactive avoidance to proactive anticipation of collisions and its effective avoidance, thereby increasing the overall safety of navigation.

Abstract

Image based reconstruction of urban environments is a challenging problem that deals with optimization of large number of variables, and has several sources of errors like the presence of dynamic objects. Since most large scale approaches make the assumption of observing static scenes, dynamic objects are relegated to the noise modelling section of such systems. This is an approach of convenience since the RANSAC based framework used to compute most multiview geometric quantities for static scenes naturally confine dynamic objects to the class of outlier measurements. However, reconstructing dynamic objects along with the static environment helps us get a complete picture of an urban environment. Such understanding can then be used for important robotic tasks like path planning for autonomous navigation, obstacle tracking and avoidance, and other areas. In this paper, we propose a system for robust SLAM that works in both static and dynamic environments. To overcome the challenge of dynamic objects in the scene, we propose a new model to incorporate semantic constraints into the reconstruction algorithm. While some of these constraints are based on multi-layered dense CRFs trained over appearance as well as motion cues, other proposed constraints can be expressed as additional terms in the bundle adjustment optimization process that does iterative refinement of 3D structure and camera / object motion trajectories. We show results on the challenging KITTI urban dataset for accuracy of motion segmentation and reconstruction of the trajectory and shape of moving objects relative to ground truth. We are able to show average relative error reduction by 41 % for moving object trajectory reconstruction relative to state-of-the-art methods like TriTrack[16], as well as on standard bundle adjustment algorithms with motion segmentation.

Abstract

In this paper we present a non-linear time scaling based formulation for computing time optimal motions along specified paths. The primary motivation behind the current work is to introduce acceleration continuity constraints within the time optimal framework. Such constraint necessitates the use of time varying controls instead of commonly used piecewise constant controls. We propose a novel extension of our previously developed concept of non-linear time scaling through which it is possible to parametrize controls as piece-wise product of a exponential and a linear function. We show that such representation leads to a very simple optimization structure with primarily linear constraints. The non-linearity has a quasi-convex structure which we reformulate into a simple difference of convex form. A sequential convex programming framework is utilised to solve the optimization as a sequence of sparse quadratic programmes. The proposed optimization is an improvement over the current state of the art frameworks which introduces acceleration continuity constraints in the time optimal framework through highly non-linear and non-convex optimizations.

Abstract

Computing time optimal motions along specified paths forms an integral part of the solution methodology for many motion planning problems. Conventionally, this optimal control problem is solved considering piece-wise constant parametrization for the control input which leads to convexity and sparsity in the optimization structure. However, it also results in discontinuous control trajectory which is difficult to track. Thus, in this paper we revisit this time optimal control problem with the primary motivation of ensuring a high degree of smoothness in the resulting motion profile. In particular, we solve it with continuity constraints in control and higher order motion derivatives like jerk, snap etc. It is clear that such constraints would necessitate the use of time varying control inputs over the commonly used piece-wise constant form. The primary contribution of the current work lies in the introduction of a C ∞ class of time scaling functions represented as parametric exponentials. This in turn allows us to represent time varying control inputs as products of parametric exponential and a polynomial functions. We present the motivation behind adopting such representation of time scaling function over more common polynomial forms, both from mathematical as well as implementation standpoint. We also show that the proposed representation of time scaling function and control input leads to a very simple optimization structure where most of the constraints are linear. The non-linearity has a quasi-convex structure which can be reformulated into a simple difference of convex form. Thus, the resulting optimization can be efficiently solved through sequential convex programming where, at each iteration, the constraints in difference of convex form are further simplified to more conservative linear constraints.

Abstract

Autonomous navigation of generic monocular quadcopter in the natural environment requires sophisticated mechanism for perception, planning and control. In this work, we have described a framework which performs perception using monocular camera and generates minimum time collision free trajectory and control for any commercial quadcopter flying through cluttered unknown environment. The proposed framework first utilizes supervised learning approach to estimate the dense depth map for video stream obtained from frontal monocular camera. This depth map is initially transformed into Ego Dynamic Space and subsequently, is used for computing locally traversable way-points utilizing binary integer programming methodology. Finally, trajectory planning and control module employs a convex programming technique to generate collision-free trajectory which follows these way-points and produces appropriate control inputs for the quadcopter. These control inputs are computed from the generated trajectory in each update. Hence, they are applicable to achieve closed-loop control similar to model predictive controller. We have demonstrated the applicability of our system in controlled indoors and in unstructured natural outdoors environment.

Abstract

Overtaking of a vehicle moving on structured roads is one of the most frequent driving behavior. In this work, we have described a Real Time Control System based framework for overtaking maneuver of autonomous vehicles. Proposed framework incorporates Intelligent Planning and Modular control modules. Intelligent Planning module of the framework enables the vehicle to intelligently select the most appropriate behavioral characteristics given the perceived operating environment. Subsequently, Modular control module reduces the search space of overtaking trajectories through an SVM based learning approach. These trajectories are then examined for possible future time collision using Velocity Obstacle. It employs non linear time scaling that provides for continuous trajectories in the space of linear and angular velocities to achieve continuous curvature overtaking maneuvers respecting velocity and acceleration bounds. Further time scaling also can scale velocities to avoid collisions and can compute a time optimal trajectory for the learned behavior. The preliminary results show the appropriateness of our proposed framework in virtual urban environment.

Abstract

In this paper, we propose a better planning technique of the standard walking gaits for a quadruped robot than the conventional successive gait transition method to realize omnidirectional static walking. The technique involved planning the sequence as well as motion of the swinging and supporting legs. The relationship between the stability margin, the stride length and the duty factor are also formulated mathematically. The proposed modified crawl gait is compared to the conventional method with respect to the above parameters geometrically as well as mathematically and is shown to have positive stability margin at all times. The successive gait transition is demonstrated on the modified crawl and rotation gaits. Computer simulations of a model quadruped robot were performed to validate the theory proposed. Experiments were performed on an actual quadruped robot to realize the omnidirectional static walking with increased stability margin.

Abstract

This work focuses on enhancing step descending ability of the modular robot proposed in [16]. The proposed robot consists of three modules connected with each other through passive joints. It is propelled using an active pair of wheels per module. Since there are no actuators at the joints, the joints are not susceptible to losing operability while traversing on rugged terrain. However with the absence of actuators, we face the issue of the robot toppling over when an abnormally large obstacle is encountered. This shortcoming is overcome with the use of compliant joints. The compliant joints are designed by employing springs of optimal stiffness, which is calculated through an optimization formulation aided with the constraints presented by the static analysis of the robot. The novelty lies in the systematic design of compliant joint for step descent. The robot is successful in climbing and descending obstacles of dimension 17 cm. Simulations of the mathematically modelled robot are carried out. The results from the same are validated on a working prototype and presented.

Abstract

This paper presents a new hierarchical architecture for parallelizing the computation intensive rapidly exploring random tree problem. The architecture resembles a tree like structure that agglutinates minimal inter-module communication of a shared memory with data integrity of a distributed memory. Another novelty of this research has been in quantitatively analysing the performance metrics of the RRT algorithm across numerous embedded hardware solutions and ultimately implementing this algorithm on an FPGA to achieve hardware level optimization that offers real time performance and economical power consumption levels. We then analyse our implementation against hardware implementation of other scalable parallel RRT methods for motion planning.