Aiming at the problem of model error and tracking dependence in the process of intelligent vehicle motion planning, an intelligent vehicle model transfer trajectory planning method based on deep reinforcement learning is proposed, which obtain an effective control action sequence directly. Firstly, an abstract model of the real environment is extracted. On this basis, Deep Deterministic Policy Gradient (DDPG) and vehicle dynamic model are adopted to jointly train a reinforcement learning model, and to decide the optimal intelligent driving maneuver. Secondly, the actual scene is transferred to equivalent virtual abstract scene by transfer model, furthermore, the control action and trajectory sequences are calculated according to trained deep reinforcement learning model. Thirdly, the optimal trajectory sequence is selected according to evaluation function in the real environment. Finally, the results demonstrate that the proposed method can deal with the problem of intelligent vehicle trajectory planning for continuous input and continuous output. The model transfer method improves the model generalization performance. Compared with the traditional trajectory planning, the proposed method output continuous rotation angle control sequence, meanwhile, the lateral control error is also reduced.
A significant broad-bandwidth near-shot-noise-limited intensity noise suppression of a single-frequency fiber laser is demonstrated based on a semiconductor optical amplifier (SOA) with optoelectronic feedback. By exploiting the gain saturation effect of the SOA and the intensity feedback loop, a maximum noise suppression of over 50 dB around the relaxation oscillation frequencies and a suppression bandwidth of up to 50 MHz are obtained. The relative intensity noise of -150 dB/Hz in the frequency range from 0.8 kHz to 50 MHz is achieved, which approaches the shot-noise limit. The obtained optical signal-to-noise ratio is more than 70 dB. This near-shot-noise-limited laser source shows important implications for the advanced fields of high-precision frequency stabilization, quantum key distribution, and gravitational wave detection.
The fusion of the heterogeneous sensors can greatly improve the environmental perception ability of mobile robots. And that the primary difficulty of heterogeneous sensors fusion is the calibration of depth scan information and plane image information for a laser rangefinder and a camera. Firstly, a coordinate transformation method from a laser rangefinder coordinates system to an optical image plane is given, and then the calibration of the camera's intrinsic parameters is achieved by “Camera Calibration Toolbox‘. Secondly, the intrinsic and extrinsic parameters are separated for calibration are proposed and compared, in which the characteristic parameters' identification is according to some characteristic points on the intersection line. Then Gaussian elimination is utilized for the initial value. Furthermore, the parameters' optimization using the non-linear least square and non-linear Gauss-Newton methods is devised for different constraints. Finally, the simulated and real experimental results demonstrate the reliability and effectiveness of extrinsic and intrinsic parameters' separated calibration, meanwhile, the real-time analysis is achieved for robotic multi-sensor fusion.
A kHz-order linewidth controllable 1550 nm single-frequency fiber laser (SFFL) is demonstrated for the first time to our best knowledge. The control of the linewidth is realized by using a low-pass filtered white Gaussian noise (WGN) signal applied on a fiber stretcher in an optical feedback loop. Utilizing WGN signals with different signal amplitudes An and different cutoff frequencies fc, the linewidths are availably controlled in a wide range from 0.8 to 353 kHz. The obtained optical signal-to-noise ratio (OSNR) is more than 72.0 dB, and the relative intensity noise (RIN) at frequency greater than 40 MHz reaches -148.5 dB/Hz which approaches the shot noise limit (-152.9 dB/Hz). This kHz-order linewidth controllable SFFL is meaningful and valuable, for optimizing the receiver sensitivity and bit error rate (BER) performance of the coherent optical communication system based on high-order quadrature amplitude modulation (QAM).
An all-optical frequency and intensity noise suppression technique of a single-frequency fiber laser is demonstrated. By exploiting the recursive noise reduction effect of a semiconductor optical amplifier (SOA) in a self-injection locked fiber laser, the frequency and intensity noise of the laser are remarkably suppressed in a significantly wide frequency range. In addition to the linewidth suppression from 3.5 kHz to 700 Hz, the frequency noise has been reduced by ∼25 dB. After suppression, the relative intensity noise (RIN) is within 5 dB of the shot noise limit at frequencies from 1.5 to 3 MHz, and the frequency range of the suppression reaches about 30 MHz. The relaxation oscillation peak is observed to shift to lower frequencies and is reduced by about 35 dB from -90 dB/Hz to -125 dB/Hz. It is believed that the achieved low noise makes the fiber laser a promising candidate in applications such as ultra-long haul coherent optical communication and LIDAR.
Abstract:The Jump Point Search (JPS) algorithm is adopted for local path planning of the driverless car under urban environment, and it is a fast search method applied in path planning. Firstly, a vector Geographic Information System (GIS) map, including Global Positioning System (GPS) position, direction, and lane information, is built for global path planning. Secondly, the GIS map database is utilized in global path planning for the driverless car. Then, the JPS algorithm is adopted to avoid the front obstacle, and to find an optimal local path for the driverless car in the urban environment. Finally, 125 different simulation experiments in the urban environment demonstrate that JPS can search out the optimal and safety path successfully, and meanwhile, it has a lower time complexity compared with the Vector Field Histogram (VFH), the Rapidly Exploring Random Tree (RRT), A*, and the Probabilistic Roadmaps (PRM) algorithms. Furthermore, JPS is validated usefully in the structured urban environment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.