Enhancing Trajectory Prediction through Self-Supervised Waypoint Distortion Prediction

Authors: Pranav Singh Chib, Pravendra Singh

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experimental results highlight a significant improvement with relative percentage differences of 22.7%/38.9%, 33.8%/36.4%, and 16.60%/23.20% in ADE/FDE for the NBA, Traj Net++, and ETH-UCY datasets, respectively, compared to the baseline methods.
Researcher Affiliation Academia 1Department of Computer Science and Engineering, Indian Institute of Technology, Roorkee, India.
Pseudocode No The paper describes the methodology using text and mathematical equations but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statements about releasing source code or a link to a code repository for the described methodology.
Open Datasets Yes We evaluate the performance of SSWDP on three trajectory datasets: NBA (Zhan et al., 2018), a synthetic partition of Traj Net++ (Kothari et al., 2021), and ETH-UCY (Lerner et al., 2007; Pellegrini et al., 2009).
Dataset Splits No The paper mentions 'validation data' in Table 6 and Section 4.6.3 but does not explicitly specify the train/validation/test dataset splits (e.g., percentages or sample counts) needed for reproduction.
Hardware Specification Yes as we processed both views in parallel rather than sequentially on the NVIDIA RTX A5000 GPU with AMD EPYC 7543 CPU
Software Dependencies No The paper does not provide specific version numbers for software components or libraries used (e.g., Python, PyTorch, CUDA, or specific ML frameworks) to reproduce the experiments.
Experiment Setup Yes The values for the noise factor (ω) and λ used in our experimentation during the training of the model are provided in Table 10. Section 4.6.3 provides insight into the choice of the noise factor.