Social-DPF: Socially Acceptable Distribution Prediction of Futures

Authors: Xiaodan Shi, Xiaowei Shao, Guangming Wu, Haoran Zhang, Zhiling Guo, Renhe Jiang, Ryosuke Shibasaki2550-2557

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments over several trajectory prediction benchmarks demonstrate that our method is able to forecast socially acceptable distributions in complex scenarios.
Researcher Affiliation Academia 1Center for Spatial Information Science, the University of Tokyo 2Earth Observation Data Integration and Fusion Research Initiative, the University of Tokyo 3Information Technology Center, the University of Tokyo
Pseudocode No The paper describes its methods in detail through text and mathematical equations but does not include a distinct pseudocode block or algorithm section.
Open Source Code No The paper does not contain any explicit statement about releasing source code or a link to a code repository for the methodology described.
Open Datasets Yes In this section, the proposed model is evaluated on two publicly available datasets: UCY(Lerner, Chrysanthou, and Lischinski 2007) and ETH(Pellegrini et al. 2009).
Dataset Splits Yes The proposed model is trained and tested on the two datasets with leave-one-out approach: trained on four sets and tested on the remaining set.
Hardware Specification Yes The experiments are implemented using Pytorch under Ubuntu 16.04 LTS using a GTX 1080 GPU.
Software Dependencies No The paper mentions 'Pytorch' and 'Ubuntu 16.04 LTS'. While Ubuntu has a version, Pytorch does not, and the rule requires specific version numbers for key software components to count as a 'Yes'.
Experiment Setup Yes The size of the hidden states of all LSTMs is set to 128. The embedding layers are composed of a fully connected layer with size 64 for Eq. 6 and 128 for the others. The batch size is set to 8 and all the methods are trained for 200 epochs. The optimizer RMSprop is used to train the proposed model with a learning rate 0.001. We clip the gradients of the LSTM with a maximum threshold of 10 to stabilize the training process. We set λ1 and λ2 in Eq. 11 as 0.1. The model outputs GMMs with three components.