Trajectron++: Dynamically-Feasible Trajectory Forecasting with Heterogeneous Data

By Tim Salzmann, Boris Ivanovic, Punarjay Chakravarty, Marco Pavone. European Conference on Computer Vision, 2020

1,349 citations recorded by the source corpus.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/2ad0f82f256dc8eb7703242f95d901c4ab3c2a06

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

1. Shaoshuai Shi
2. Benjamin Sapp
3. Dengxin Dai
4. Bernt Schiele
5. Li Jiang
6. Hang Zhao
7. Xinshuo Weng
8. Luyao Ye

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Xiaogang Wang
3. Dacheng Tao
4. Jitendra Malik
5. Ming-Hsuan Yang
6. Trevor Darrell
7. Bernt Schiele
8. Alan L. Yuille

In Signal Processing

1. Jie Zhou
2. Benjamin Sapp
3. Yuning Chai
4. Jitendra Malik
5. Charles Ruizhongtai Qi
6. Ye Yuan
7. Jiwen Lu
8. Dengxin Dai

Citations in the corpus

• AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting (2021, methodology): “Alternatively, approaches like [45, 18] first use social models to produce social features of each agent at each independent timestep and then apply temporal models to summarize the social features over time for each agent.”
• HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction (2022, methodology): “Since social interactions are ubiquitous in traffic scenarios and significantly impact the future motions of traffic agents, many motion prediction approaches have considered the dependencies between agents’ behaviors and reasoned agent-agent interactions using social pooling [2,13,23], graph neural”
• Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset (2021, methodology): “For methods that provide explicit or implicit future probability distributions, the likelihood of the ground truth future trajectory can be used as a metric [8, 30, 27, 28].”
• A Survey on Trajectory-Prediction Methods for Autonomous Driving (2022, background): “Recently, a graph-structured recurrent model named Trajectron++ is proposed in [145] to produce dynamically-feasible future trajectories, which represents a scene as a directed spatio-temporal graph and is designed to be tightly integrated with the planning system for AVs.”
• Motion Transformer with Global Intention Localization and Local Movement Refinement (2022, background): “Some other works [9, 21, 33, 37, 41] parameterize multi-modal predictions with Gaussian Mixture Models (GMMs) to generate compact distribution.”
• From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting (2020, background): “Trajectron++ [36] represents agent’s trajectories in a graph structured recurrent network for scene compliant trajectory forecasting, taking into account the interaction with a diverse set of agents.”
• Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion (2022, methodology): “We observe that Trajectron++ performs similarly to MID for short-term forecasting yet a little deviates from the ground truth path for longer prediction.”