Toward a More Complete, Flexible, and Safer Speed Planning for Autonomous Driving via Convex Optimization.

In this paper, we present a complete, flexible and safe convex-optimization-based method to solve speed planning problems over a fixed path for autonomous driving in both static and dynamic environments. Our contributions are five fold. First, we summarize the most common constraints raised in various autonomous driving scenarios as the requirements for speed planner developments and metrics to measure the capacity of existing speed planners roughly for autonomous driving. Second, we introduce a more general, flexible and complete speed planning mathematical model including all the summarized constraints compared to the state-of-the-art speed planners, which addresses limitations of existing methods and is able to provide smooth, safety-guaranteed, dynamic-feasible, and time-efficient speed profiles. Third, we emphasize comfort while guaranteeing fundamental motion safety without sacrificing the mobility of cars by treating the comfort box constraint as a semi-hard constraint in optimization via slack variables and penalty functions, which distinguishes our method from existing ones. Fourth, we demonstrate that our problem preserves convexity with the added constraints, thus global optimality of solutions is guaranteed. Fifth, we showcase how our formulation can be used in various autonomous driving scenarios by providing several challenging case studies in both static and dynamic environments. A range of numerical experiments and challenging realistic speed planning case studies have depicted that the proposed method outperforms existing speed planners for autonomous driving in terms of constraint type covered, optimality, safety, mobility and flexibility.

Infrared species tomography of a transient flow field using Kalman filtering.

In infrared species tomography, the unknown concentration distribution of a species is inferred from the attenuation of multiple collimated light beams shone through the measurement field. The resulting set of linear equations is rank-deficient, so prior assumptions about the smoothness and nonnegativity of the distribution must be imposed to recover a solution. This paper describes how the Kalman filter can be used to incorporate additional information about the time evolution of the distribution into the reconstruction. Results show that, although performing a series of static reconstructions is more accurate at low levels of measurement noise, the Kalman filter becomes advantageous when the measurements are corrupted with high levels of noise. The Kalman filter also enables signal multiplexing, which can help achieve the high sampling rates needed to resolve turbulent flow phenomena.

Multistep Prediction of Dynamic Systems With Recurrent Neural Networks.

In this paper, we address the state initialization problem in recurrent neural networks (RNNs), which seeks proper values for the RNN initial states at the beginning of a prediction interval. The proposed methods employ various forms of neural networks (NNs) to generate proper initial state values for RNNs. A variety of RNNs are trained using the proposed NN initialization schemes for modeling two aerial vehicles, a helicopter and a quadrotor, from experimental data. It is shown that the RNN initialized by the NN-based initialization method outperforms the washout method which is commonly used to initialize RNNs. Furthermore, a comprehensive study of RNNs trained for multistep prediction of the two aerial vehicles is presented. The multistep prediction of the quadrotor is enhanced using a hybrid model, which combines a simplified physics-based motion model of the vehicle with RNNs. While the maximum translational and rotational velocities in the Quadrotor data set are about 4 m/s and 3.8 rad/s, respectively, the hybrid model produces predictions, over 1.9 s, which remain within 9 cm/s and 0.12 rad/s of the measured translational and rotational velocities, with 99% confidence on the test data set.