Search

This letter presents a free space trajectory optimization algorithm for autonomous driving, which decouples the collision-free trajectory generation problem into a Dual-Loop Iterative Anchoring Path Smoothing (DL-IAPS) problem and a Piecewise-Jerk Speed Optimization (PJSO) problem. The work leads to remarkable driving performance improvements including more robust and precise collision avoidance, higher control feasibility, higher computation efficiency and stricter driving comfort guarantee, compared with other existing algorithms. The advantages of our algorithm are attributed to our fast iterative collision checks with exact vehicle/obstacle shapes, strict non-holonomic dynamic constraints and accurate kinematics-based speed optimization. It has been validated that, through batch simulation and road experiments, compared with prior works, our algorithm is with the highest robustness and capable to maintain the lowest failure rate ( $\sim\!\text{7}\%$ ) at nearly all test conditions, achieves 10x faster computational speed than other planners, fulfills $\text{100}\%$ driving-comfort standards in complex driving scenarios, and does not induce significant time increase as boundaries or obstacles scale up.

We present a learning-based planner that aims to robustly drive a vehicle by mimicking human drivers' driving behavior. We leverage a mid-to-mid approach that allows us to manipulate the input to our imitation learning network freely. With that in mind, we propose a novel feedback synthesizer for data augmentation. It allows our agent to gain more driving experience in various previously unseen environments that are likely to encounter, thus improving overall performance. This is in contrast to prior works that rely purely on random synthesizers. Furthermore, rather than completely commit to imitating, we introduce task losses that penalize undesirable behaviors, such as collision, off-road, and so on. Unlike prior works, this is done by introducing a differentiable vehicle rasterizer that directly converts the waypoints output by the network into images. This effectively avoids the usage of heavyweight ConvLSTM networks, therefore, yields a faster model inference time. About the network architecture, we exploit an attention mechanism that allows the network to reason critical objects in the scene and produce better interpretable attention heatmaps. To further enhance the safety and robustness of the network, we add an optional optimization-based post-processing planner improving the driving comfort. We comprehensively validate our method's effectiveness in different scenarios that are specifically created for evaluating self-driving vehicles. Results demonstrate that our learning-based planner achieves high intelligence and can handle complex situations. Detailed ablation and visualization analysis are included to further demonstrate each of our proposed modules' effectiveness in our method., 8 pages, 10 figures, Accepted by IROS 2021

This paper presents an optimization-based collision avoidance trajectory generation method for autonomous driving in free-space environments, with enhanced robustness, driving comfort and efficiency. Starting from the hybrid optimization-based framework, we introduces two warm start methods, temporal and dual variable warm starts, to improve the efficiency. We also reformulate the problem to improve the robustness and efficiency. We name this new algorithm TDR-OBCA. With these changes, compared with original hybrid optimization we achieve a 96.67% failure rate decrease with respect to initial conditions, 13.53% increase in driving comforts and 3.33% to 44.82% increase in planner efficiency as obstacles number scales. We validate our results in hundreds of simulation scenarios and hundreds of hours of public road tests in both U.S. and China. Our source code is available at https://github.com/ApolloAuto/apollo.

An intracavity frequency-tripling of a diode-edge-pumped passively Q-switched 1 064 nm Nd∶YAG laser is presented to generate high power 355 nm UV laser.Several essential technologies are put forward to achieve the best beam quality such as a volume grating to maintain quasi phase matching with narrow linewidth,optimization and thermal effects compensation for cavity.The task first takes advantage of volume grating and two CBO crystals as SHG and THG nonlinear optical conversion material to obtain high UV laser power output more than 4 W,light quality factor M22.5,meanwhile it is the first time to realize thermal effect using 45° Faraday rotator.The achievement is expected to be the popular light source system in lithography instead of conventional excimer laser.

There is a significant Poisson effect for knitted fabric under tensile deformation. It is an important parameter for practical pattern design, numerical simulation of garment pressure distribution and garment dressing system. However, it is still difficult to measure the fabric Poisson ratio quickly and accurately. In this paper, a method for testing the elastic knitted fabric Poisson ratio and modulus was proposed based on orthotropic theory and strip biaxial tensile test. The fabric’s Poisson ratio and Young’s modulus are identified by linear regression, while the obtained values are validated by uniaxial tensile tests.