LSTM based trajectory prediction model for cyclist utilizing multiple interactions with environment

•A unified LSTM network framework models cyclist's interaction with the environment.•Road key points address the interaction with road and static obstacles.•The focal attention mechanism improves LSTM by focusing on more relevant features.•MI-LSTM acquires the knowledge of interactions and outperforms the typical state-of-the-art approaches in most cases. The cyclist trajectory prediction is critical for the local path planning of autonomous vehicles. Based on the assumption that cyclist's movement is limited by its dynamics and subjected to interactions with environments, a novel LSTM based cyclist trajectory prediction model which utilizes multiple interactions with surroundings and motion feature in a unified framework is proposed. Road features describing road boundary and static obstacles are employed to address cyclist's interaction with the road. To address interactions with pedestrians, other cyclists and vehicles, object features including object attributes and relative positions are utilized. The focal attention mechanism is employed to reveal the importance of features at each time-steps. By feeding features into LSTM encoder, the movement in the next two seconds is predicted. Experiments were conducted on two datasets, and results show that the presented model outperforms the state-of-art models in most cases.