Depth perception is a key component for autonomous systems that interact in the real world, such as delivery robots, warehouse robots, and self-driving cars. Tasks in autonomous robotics such as 3D object recognition, simultaneous localization and mapping (SLAM), path planning and navigation, require some form of 3D spatial information. Depth perception is a long-standing research problem in computer vision and robotics and has had a long history. Many approaches using deep learning, ranging from structure from motion, shape-from-X, monocular, binocular, and multi-view stereo, have yielded acceptable results. However, there are several shortcomings of these methods such as requiring expensive hardware, needing supervised training data, no ground truth data for comparison, and disregard for occlusion. In order to address these shortcomings, this work proposes a new deep convolutional generative adversarial network architecture, called Y-GAN, that uses data from three cameras to estimate a depth map for each frame in a multi-camera video stream.
Reliable navigation like expert human drivers in urban environments is a critical capability for autonomous vehicles. Traditional methods for autonomous driving are implemented with many building blocks from perception, planning and control, making them difficult to generalize to varied scenarios due to complex assumptions and interdependencies. In this paper, we develop an end-to-end trajectory generation method based on imitation learning. It can extract spatiotemporal features from the front-view camera images for scene understanding, then generate collision-free trajectories several seconds into the future. The proposed network consists of three sub-networks, which are selectively activated for three common driving tasks: keep straight, turn left and turn right. The experimental results suggest that under various weather and lighting conditions, our network can reliably generate trajectories in different urban environments, such as turning at intersections and slowing down for collision avoidance. Furthermore, by integrating the proposed network into a navigation system, good generalization performance is presented in an unseen simulated world for autonomous driving on different types of vehicles, such as cars and trucks.
Recent applications of autonomous agents and robots, for example, self-driving cars, scenario-based trainers, exploration robots, service robots, have brought attention to crucial trust-related problems associated with the current generation of artificial intelligence (AI) systems. AI systems particularly dominated by the connectionist deep learning neural network approach lack capabilities of explaining their decisions and actions to others, despite their great successes. They are fundamentally non-intuitive black boxes, which renders their decision or actions opaque, making it difficult to trust them in safety-critical applications. The recent stance on the explainability of AI systems has witnessed several works on eXplainable Artificial Intelligence; however, most of the studies have focused on data-driven XAI systems applied in computational sciences. Studies addressing the increasingly pervasive goal-driven agents and robots are still missing. This paper reviews works on explainable goal-driven intelligent agents and robots, focusing on techniques for explaining and communicating agents perceptual functions (for example, senses, vision, etc.) and cognitive reasoning (for example, beliefs, desires, intention, plans, and goals) with humans in the loop. The review highlights key strategies that emphasize transparency and understandability, and continual learning for explainability. Finally, the paper presents requirements for explainability and suggests a roadmap for the possible realization of effective goal-driven explainable agents and robots
Robot motion planning is central to real-world autonomous applications, such as self-driving cars, persistence surveillance, and robotic arm manipulation. One challenge in motion planning is generating control signals for nonlinear systems that result in obstacle free paths through dynamic environments. In this paper, we propose Control Barrier Function guided Rapidly-exploring Random Trees (CBF-RRT), a sampling-based motion planning algorithm for continuous-time nonlinear systems in dynamic environments. The algorithm focuses on two objectives: efficiently generating feasible controls that steer the system toward a goal region, and handling environments with dynamical obstacles in continuous time. We formulate the control synthesis problem as a Quadratic Program (QP) that enforces Control Barrier Function (CBF) constraints to achieve obstacle avoidance. Additionally, CBF-RRT does not require nearest neighbor or collision checks when sampling, which greatly reduce the run-time overhead when compared to standard RRT variants.
Machine-learning driven safety-critical autonomous systems, such as self-driving cars, must be able to detect situations where its trained model is not able to make a trustworthy prediction. Often viewed as a black-box, it is non-obvious to determine when a model will make a safe decision and when it will make an erroneous, perhaps life-threatening one. Prior work on novelty detection deal with highly structured data and do not translate well to dynamic, real-world situations. This paper proposes a multi-step framework for the detection of novel scenarios in vision-based autonomous systems by leveraging information learned by the trained prediction model and a new image similarity metric. We demonstrate the efficacy of this method through experiments on a real-world driving dataset as well as on our in-house indoor racing environment.
In this paper, a synergistic combination of deep reinforcement learning and hierarchical game theory is proposed as a modeling framework for behavioral predictions of drivers in highway driving scenarios. The need for a modeling framework that can address multiple human-human and human-automation interactions, where all the agents can be modeled as decision makers simultaneously, is the main motivation behind this work. Such a modeling framework may be utilized for the validation and verification of autonomous vehicles: It is estimated that for an autonomous vehicle to reach the same safety level of cars with drivers, millions of miles of driving tests are required. The modeling framework presented in this paper may be used in a high-fidelity traffic simulator consisting of multiple human decision makers to reduce the time and effort spent for testing by allowing safe and quick assessment of self-driving algorithms. To demonstrate the fidelity of the proposed modeling framework, game theoretical driver models are compared with real human driver behavior patterns extracted from traffic data.
In motion planning problems for autonomous robots, such as self-driving cars, the robot must ensure that its planned path is not in close proximity to obstacles in the environment. However, the problem of evaluating the proximity is generally non-convex and serves as a significant computational bottleneck for motion planning algorithms. In this paper, we present methods for a general class of absolutely continuous parametric curves to compute: (i) the minimum separating distance, (ii) tolerance verification, and (iii) collision detection. Our methods efficiently compute bounds on obstacle proximity by bounding the curve in a convex region. This bound is based on an upper bound on the curve arc length that can be expressed in closed form for a useful class of parametric curves including curves with trigonometric or polynomial bases. We demonstrate the computational efficiency and accuracy of our approach through numerical simulations of several proximity problems.
During the development of autonomous systems such as driverless cars, it is important to characterize the scenarios that are most likely to result in failure. Adaptive Stress Testing (AST) provides a way to search for the most-likely failure scenario as a Markov decision process (MDP). Our previous work used a deep reinforcement learning (DRL) solver to identify likely failure scenarios. However, the solver's use of a feed-forward neural network with a discretized space of possible initial conditions poses two major problems. First, the system is not treated as a black box, in that it requires analyzing the internal state of the system, which leads to considerable implementation complexities. Second, in order to simulate realistic settings, a new instance of the solver needs to be run for each initial condition. Running a new solver for each initial condition not only significantly increases the computational complexity, but also disregards the underlying relationship between similar initial conditions. We provide a solution to both problems by employing a recurrent neural network that takes a set of initial conditions from a continuous space as input. This approach enables robust and efficient detection of failures because the solution generalizes across the entire space of initial conditions. By simulating an instance where an autonomous car drives while a pedestrian is crossing a road, we demonstrate the solver is now capable of finding solutions for problems that would have previously been intractable.
Semantic Segmentation is an important module for autonomous robots such as self-driving cars. The advantage of video segmentation approaches compared to single image segmentation is that temporal image information is considered, and their performance increases due to this. Hence, single image segmentation approaches are extended by recurrent units such as convolutional LSTM (convLSTM) cells, which are placed at suitable positions in the basic network architecture. However, a major critique of video segmentation approaches based on recurrent neural networks is their large parameter count and their computational complexity, and so, their inference time of one video frame takes up to 66 percent longer than their basic version. Inspired by the success of the spatial and depthwise separable convolutional neural networks, we generalize these techniques for convLSTMs in this work, so that the number of parameters and the required FLOPs are reduced significantly. Experiments on different datasets show that the segmentation approaches using the proposed, modified convLSTM cells achieve similar or slightly worse accuracy, but are up to 15 percent faster on a GPU than the ones using the standard convLSTM cells. Furthermore, a new evaluation metric is introduced, which measures the amount of flickering pixels in the segmented video sequence.
With a great amount of research going on in the field of autonomous vehicles or self-driving cars, there has been considerable progress in road detection and tracking algorithms. Most of these algorithms use GPS to handle road junctions and its subsequent decisions. However, there are places in the urban environment where it becomes difficult to get GPS fixes which render the junction decision handling erroneous or possibly risky. Vision-based junction detection, however, does not have such problems. This paper proposes a novel deep convolutional neural network architecture for disambiguation of junctions from roads with a high degree of accuracy. This network is benchmarked against other well known classifying network architectures like AlexNet and VGGnet. Further, we discuss a potential road navigation methodology which uses the proposed network model. We conclude by performing an experimental validation of the trained network and the navigational method on the roads of the Indian Institute of Science (IISc).