Abstract

In this paper, we present IVO: Inverse Velocity Obstacles an egocentric framework that improves the real time implementation. The proposed method stems from the concept of velocity obstacle and can be applied for both single agent and multi-agent system. It focuses on computing collision free maneuvers without any knowledge or assumption on the pose and the velocity of the robot. This is primarily achieved by reformulating the velocity obstacle to adapt to an ego-centric framework. This is a significant step towards improving real time implementations of collision avoidance in dynamic environments as there is no dependency on state estimation techniques to infer the robot pose and velocity. We evaluate IVO for both single agent and multi-agent in different scenarios and show it’s efficacy over the existing formulations. We also show the real time scalability of the proposed methodology.

Abstract

Monocular SLAM is a well-studied problem and has shown significant progress in recent years, but still, challenges remain in creating a rich semantic description of the scene. Feature-based visual SLAMs are vulnerable to erroneous pose estimates due to insufficient tracking of mapped points or motion induced errors such as in large or in-place rotations. We present a new SLAM framework in which we use monocular edge based SLAM [1], along with category level models, to localize objects in the scene as well as improve the camera trajectory. In monocular SLAM systems, the camera track tends to break in conditions with abrupt motion which leads to reduction in the number of 2D point correspondences. In order to tackle this problem, we propose the first most principled formulation of its kind which integrates object category models in the core SLAM back-end to jointly optimize for the camera trajectory, object poses along with its shape and 3D structure. We show that our joint optimization is able to recover a better camera trajectory in such cases, as compared to Edge SLAM. Moreover, this method gives a better visualization incorporating object representations in the scene along with the 3D structure of the base SLAM system, which makes it useful for augmented reality (AR) applications

Abstract

In this paper, we present a novel control law for longitudinal speed control of autonomous vehicles. The key contributions of the proposed work include the design of a control law that reactively integrates the longitudinal surface gradient of the road into its operation. In contrast to the existing works, we found that integrating the path gradient into the control framework improves the speed tracking efficacy. Since the control law is implemented over a shrinking domain scheme, it minimizes the integrated error by recomputing the control inputs at every discretized step and consequently provides less reaction time. This makes our control law suitable for motion planning frameworks that are operating at high frequencies. Furthermore, our work is implemented using a generalized vehicle model and can be easily extended to other classes of vehicles. The performance of gradient aware - shrinking domain based controller is implemented and tested on an electric car. Results from the tests show the robustness of our control law for speed tracking efficiency on terrain with varying gradient while also considering stringent time constraints imposed by the planning framework.

Abstract

Multi-agent learning provides a potential framework for learning and simulating traffic behaviors. This paper proposes a novel architecture to learn multiple driving behaviors in a traffic scenario. The proposed architecture can learn multiple behaviors independently as well as simultaneously. We take advantage of the homogeneity of agents and learn in a parameter sharing paradigm. To further speed up the training process asynchronous updates are employed into the architecture. While learning different behaviors simultaneously, the given framework was also able to learn cooperation between the agents, without any explicit communication. We applied this framework to learn two important behaviors in driving: 1) Lane-Keeping and 2) Over-Taking. Results indicate faster convergence and learning of a more generic behavior, that is scalable to any number of agents. When compared the results with existing approaches, our results indicate equal and even better performance in some cases.

Abstract

Multi-agent learning provides a potential framework for learning and simulating traffic behaviors. This paper proposes a novel architecture to learn multiple driving behaviors in a traffic scenario. The proposed architecture can learn multiple behaviors independently as well as simultaneously. We take advantage of the homogeneity of agents and learn in a parameter sharing paradigm. To further speed up the training process asynchronous updates are employed into the architecture. While learning different behaviors simultaneously, the given framework was also able to learn cooperation between the agents, without any explicit communication. We applied this framework to learn two important behaviors in driving: 1) Lane-Keeping and 2) Over-Taking. Results indicate faster convergence and learning of a more generic behavior, that is scalable to any number of agents. When compared the results with existing approaches, our results indicate equal and even better performance in some cases.

Abstract

In this paper, we propose a new model predictive control (MPC) formulation for autonomous driving. The novelty of our MPC stems from the following results. Firstly, we adopt an alternating minimization approach wherein linear velocities and angular accelerations are alternately optimized. We show that in contrast to the joint optimization, the alternating minimization exploits the structure of the problem better, which in turn translates to reduction in computation time. Secondly, our MPC explicitly incorporates the time dependent non-linear actuator dynamics that captures the transient response of the vehicle for a given commanded velocity. This added complexity improves the predictive component of MPC resulting in improved margin of inter-vehicle distance during maneuvers like overtaking, lane-change, etc. Although, past works have also incorporated actuator dynamics within MPC, there has been very few attempts towards coupling actuator dynamics to collision avoidance constraints through the non-holonomic motion model of the vehicle and analyzing the resulting behavior. We use a high fidelity simulator to benchmark our actuator dynamics augmented MPC with other related approaches in terms of metrics like inter-vehicle distance, trajectory smoothness, and velocity overshoot.

Abstract

Robotic grippers have been designed for grasping a wide variety of objects. This paper presents a novel design of a flexible gripper suitable for gripping circular objects having variable curvatures and different textures. Two rubber belts form the gripper arms, which are used for gripping objects. These rubber belts are attached to DC motors. The motors are fitted in the gripper base. Magnets are attached on the other ends along with an interlocking mechanism. The primary actuation in the gripper is brought about by the Shape Memory Alloy (SMA) wire fitted along the inner side of the rubber belts. On energizing the SMA, the rubber belts bend along with the pre-programmed SMA and the magnets on the two belts come closer. Subsequently, locking is achieved. This forms a loop around the gripping object. The grip of the rubber belts around the object is further tightened by winding them around the shafts of the motors to which they are attached. This helps the gripper to firmly grasp objects of variable diameters. Gripping has been successfully tested on pipes, metal poles, trees with thin and thick stems.

Abstract

We present a monocular object parsing framework for consistent keypoint localization by capturing temporal correlation on sequential data. In this paper, we propose a novel recurrent network based architecture to model longrange dependencies between intermediate features which are highly useful in tasks like keypoint localization and tracking. We leverage the expressiveness of the popular stacked hourglass architecture and augment it by adopting memory units between intermediate layers of the network with weights shared across stages for video frames. We observe that this weight sharing scheme not only enables us to frame hourglass architecture as a recurrent network but also prove to be highly effective in producing increasingly refined estimates for sequential tasks. Furthermore, we propose a new memory cell, we call CoordConvGRU which learns to selectively preserve spatiotemporal correlation and showcase our results on the keypoint localization task. The experiments show that our approach is able to model the motion dynamics between the frames and significantly outperforms the baseline hourglass network. Even though our network is trained on a synthetically rendered dataset, we observe that with minimal fine tuning on 300 real images we are able to achieve performance at par with various state-of-the-art methods trained with the same level of supervisory inputs. By using a simpler architecture than other methods enables us to run it in real time on a standard GPU which is desirable for such applications. Finally, we make our architectures and 524 annotated sequences of cars from KITII dataset publicly available.

Abstract

This paper discusses the design and implementation of the Modular Pipe Climber inside ASTM D1785 - 15e1 standard pipes [1]. The robot has three tracks which operate independently and are mounted on three modules which are oriented at 120° to each other. Tracks provide for greater surface traction compared to wheels [2]. The tracks are pushed onto the inner wall of the pipe by passive springs to maintain contact with the pipe during vertical climb and while turning in bends. The modules have the provision to compress asymmetrically, which enables the robot to take turns in bends in all directions. The motor torque required by the robot and the desired spring stiffness are calculated at quasi-static and static equilibriums during vertical climb. The robot is further simulated and analyzed in ADAMS MSC. The prototype built based on the obtained values is experimented on, in complex pipe networks. Differential speed is employed when turning in bends to improve the efficiency and reduce the stresses experienced by the robot.

Abstract

This paper introduces the Omnidirectional Tractable Three Module Robot for traversing inside complex pipe networks. The robot consists of three omnidirectional modules fixed 120 apart circumferentially which can rotate about their own axis allowing holonomic motion of the robot. The holonomic motion enables the robot to overcome motion singularity when negotiating T-junctions and further allows the robot to arrive in a preferred orientation while taking turns inside a pipe. We have developed a closed-form kinematic model for the robot in the paper and propose the Motion Singularity Region that the robot needs to avoid while negotiating T-junction. The design and motion capabilities of the robot are demonstrated both by conducting simulations in MSC ADAMS on a simplified lumped-model of the robot and with experiments on its physical embodiment.