Search

Forecasting pedestrians' future trajectory in unknown complex environments is essential to autonomous navigation in real‐world applications, for example, for self‐driving cars and collision warnings. However, modern observed trajectory‐based prediction methods may easily over‐fit to complex or rare scenes because they do not entirely understand the correlations between scenes and trajectories. To address the over‐fitting problem, an Inverse Reinforcement Learning for Scene‐oriented Trajectory Prediction (IRLSOT) is proposed in this work. The authors' method can be divided into three modules. First, the inverse reinforcement learning module generates the optimal policy by extracting features from scenes and pedestrians' observed trajectories. A lightweight ENet is used to extract features from scenes. Afterwards, the path sampling module introduces a Gumbel Softmax Trick (GST) to improve the accuracy of optimal policy sampling. Different paths are generated on the basis of the optimal policies. Finally, the information fusion module uses the proposed Scene Based Attention (SBA) to fuse the path and trajectory information, then outputs the predicted trajectories. Comparison results show that IRLSOT improves performance on Stanford Drone Database(SDD) by 5.9%$\%$. Furthermore, the authors' test IRLSOT on multi‐agent scenarios and the authors' own data sets, and results demonstrate that IRLSOT can enhance the generalization of trajectory prediction to rare or new scenes. [ABSTRACT FROM AUTHOR]

The stress effect of cadmium absorption between aloe and Brassica junica was studied through a simulation experiment with different cadmium contents in soil. The results showed that the growth characteristics, biomass and cadmium content of aloe and B. junica plants were related to pH and cadmium content in the soil. When aloe was intercropped with B. junica, soil pH was higher than that of single planting, showing that intercropping aloe and B. junica can reduce aloe's absorption of Cd. When Cd content in the soil was high, the absorption coefficient of aloe was lower than that of B. junica, and Cd content in the leaves of intercropped aloe was 15.8%-79.2% lower than that of aloe cropped only. In addition, planting B. junica in the soil with different contents of Cd had certain stress effect on aloe's absorption of Cd, thereby protecting aloe well, improving safety of aloe planting and showing its potential tor application in phytoremediation. [ABSTRACT FROM AUTHOR]

The stress effect of cadmium absorption between aloe and Solarium nigrum L was studied through a simulation experiment with different cadmium contents in soil. The results showed that the growth characteristics, biomass and Cd content in the plants of aloe and S. nigrum L were closely related to Cd content in the soil, and S. nigrum L and aloe had a strong tolerance to Cd in the experiment. pH of rhizosphere soil with S. nigrum L and aloe planted was generally higher than that of non-rhizosphere soil, which is related to the planting pattern. Compared with aloe, S. nigrum L had a stronger capacity to accumulate Cd, and intercropping S. nigrum L and aloe could inhibit aloe's absorption of Cd, which is favorable to the sate planting of aloe. In addition, S. nigrum L has the potential to restore polluted soil. [ABSTRACT FROM AUTHOR]