Trajectory distributions: A new description of movement for trajectory prediction

Abstract

Trajectory prediction is a fundamental and challenging task for numerous applications, such as autonomous driving and intelligent robots. Current works typically treat pedestrian trajectories as a series of 2D point coordinates. However, in real scenarios, the trajectory often exhibits randomness, and has its own probability distribution. Inspired by this observation and other movement characteristics of pedestrians, we propose a simple and intuitive movement description called a trajectory distribution, which maps the coordinates of the pedestrian trajectory to a 2D Gaussian distribution in space. Based on this novel description, we develop a new trajectory prediction method, which we call the social probability method. The method combines trajectory distributions and powerful convolutional recurrent neural networks. Both the input and output of our method are trajectory distributions, which provide the recurrent neural network with sufficient spatial and random information about moving pedestrians. Furthermore, the social probability method extracts spatio-temporal features directly from the new movement description to generate robust and accurate predictions. Experiments on public benchmark datasets show the effectiveness of the proposed method.

Realization Path of College Students’ Network Ideological and Political Teaching System in the New Media Environment

“…Lv et al proposed a new technology. For applications such as smart home and smart navigation, this new media method has certain advantages in trajectory prediction [8]. Huang et al proposed a new method to ensure the stable operation of online classrooms.…”

A survey of urban visual analytics: Advances and future directions

“…Many complicated models, particularly those based on deep learning, are increasingly applied in urban scenarios, such as autonomous driving, trajectory prediction [205], and urban flow analysis [2,206,207]. Despite the excellent results achieved, the dynamic and complex urban environment poses challenges when deploying such models in the real world [77][78][79].…”

Marine Drifting Trajectory Prediction Based on LSTM-DNN Algorithm

“…Nowadays, massive efforts have been down in predicting the trajectory, including human motion [6,7], intelligent vehicles [8][9][10][11], service robots [12], surveillance systems [13,14], wind power generation [15,16], magnetic field intensity [17,18], and ship trajectory [19,20]. The long short-term memory (LSTM) is a neural network that is responsible for calculating the dependence between observations in a time series.…”