Driving Intention Recognition of Surrounding Vehicles Based on a Time-Sequenced Weights Hidden Markov Model for Autonomous Driving.

Accurate perception, especially situational awareness, is central to the evolution of autonomous driving. This necessitates understanding both the traffic conditions and driving intentions of surrounding vehicles. Given the unobservable nature of driving intentions, the hidden Markov model (HMM) has emerged as a popular tool for intention recognition, owing to its ability to relate observable and hidden variables. However, HMM does not account for the inconsistencies present in time series data, which are crucial for intention recognition. Specifically, HMM overlooks the fact that recent observations offer more reliable insights into a vehicle's driving intention. To address the aforementioned limitations, we introduce a time-sequenced weights hidden Markov model (TSWHMM). This model amplifies the significance of recent observations in recognition by integrating a discount factor during the observation sequence probability computation, making it more aligned with practical requirements. Regarding the model's input, in addition to easily accessible states of a target vehicle, such as lateral speed and heading angle, we also introduced lane hazard factors that reflect collision risks to capture the traffic environment information surrounding the vehicle. Experiments on the HighD dataset show that TSWHMM achieves recognition accuracies of 94.9% and 93.4% for left and right lane changes, surpassing both HMM and recurrent neural networks (RNN). Moreover, TSWHMM recognizes lane-changing intentions earlier than its counterparts. In tests involving more complex roundabout scenarios, TSWHMM achieves an accuracy of 87.3% and can recognize vehicles' intentions to exit the roundabout 2.09 s in advance.

Synthesis of the bismuth oxyhalide solid solutions with tunable band gap and photocatalytic activities.

Three series of BiOM(x)R(1-x) (M, R = Cl, Br, I) solid solutions were systematically synthesized through a low-temperature precipitation. These solid solutions were characterized by XRD, FESEM, TEM, EDS, UV-vis spectra, nitrogen sorption/desorption, and PL. The tunable band gaps of the as-prepared solid solutions were realized via only changing the molar ratio of two halide ions. Meanwhile, the influence of citric acid in the formations of controllable morphological structures was discussed to study the growth mechanism of solid solutions. The photocatalytic activities of the bismuth oxyhalide solid solutions have also been investigated by the degradation of Rhodamine-B (RhB) under visible light irradiation. The optimized solid solutions possess higher photocatalytic activity than pure ones [BiOM (M = Cl, Br, I)] due to the broadened range of visible light response and the reduced recombination rate of electron-holes pairs. The results show that the synthesis of BiOM(x)R(1-x) (M, R = Cl, Br, I) solid solutions have profound significance for the design of the novel photocatalyst materials.

One-pot solvothermal synthesis of uniform layer-by-layer self-assembled ultrathin hexagonal Gd2O2S nanoplates and luminescent properties from single doped Eu3+ and codoped Er3+, Yb3+.

Uniform Gd(2)O(2)S flower-like nano-assemblies were prepared through one-pot mild solvothermal synthesis. The parallel nanoplates are the building blocks, ∼3 nm in thickness and 20-30 in diameter. Ethanediamine, the main solvent, plays an important role in dissolving a large amount of sulphur and producing active S(2-) ions, which results in the direct formation of Gd(2)O(2)S. Oleylamine, the capping agent, controls the growth of the plate-like structure. Under UV excitation, the Gd(2)O(2)S:Eu(3+) nano-phosphor shows good red luminescence with a main emission peak at 627 nm. Under 980 nm laser excitation, Gd(2)O(2)S:xYb(3+),1%Er(3+) nano-phosphors exhibit a tuneable emission, shifting from greenish-yellow to orange-yellow, with increasing Yb(3+) content.