2022 International Conference on Robotics and Automation (ICRA) 2022
DOI: 10.1109/icra46639.2022.9812337
|View full text |Cite
|
Sign up to set email alerts
|

KEMP: Keyframe-Based Hierarchical End-to-End Deep Model for Long- Term Trajectory Prediction

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1
1

Relationship

1
6

Authors

Journals

citations
Cited by 12 publications
(4 citation statements)
references
References 19 publications
0
4
0
Order By: Relevance
“…This is a reasonable assumption, because there are many techniques that predict the future trajectories of obstacles. For example, in the recently developed autonomous driving research community, there is a whole area devoted to predicting the future trajectories of agents, including vehicles, bicyclists, and pedestrians, in the traffic scene Gu et al (2021); Lu et al (2022). After getting information from the environment via perception, the robot first predicts the future trajectories of other agents in the scene and then plans its own trajectory.…”
Section: Problem Formulationmentioning
confidence: 99%
“…This is a reasonable assumption, because there are many techniques that predict the future trajectories of obstacles. For example, in the recently developed autonomous driving research community, there is a whole area devoted to predicting the future trajectories of agents, including vehicles, bicyclists, and pedestrians, in the traffic scene Gu et al (2021); Lu et al (2022). After getting information from the environment via perception, the robot first predicts the future trajectories of other agents in the scene and then plans its own trajectory.…”
Section: Problem Formulationmentioning
confidence: 99%
“…This is a reasonable assumption, because there are many techniques that predict the future trajectories of obstacles. For example, in the recently developed autonomous driving research community, there is a whole area devoted to predicting the future trajectories of agents, including vehicles, bicyclists, and pedestrians, in the traffic scene (Gu et al, 2021;Lu et al, 2022).…”
Section: Problem Formulationmentioning
confidence: 99%
“…In essence, we are considering the trajectory planning problem in the presence of “known unknowns.” This is a reasonable assumption, because there are many techniques that predict the future trajectories of obstacles. For example, in the recently developed autonomous driving research community, there is a whole area devoted to predicting the future trajectories of agents, including vehicles, bicyclists, and pedestrians, in the traffic scene (Gu et al, 2021; Lu et al, 2022). After getting information from the environment via perception, the robot first predicts the future trajectories of other agents in the scene and then plans its own trajectory.…”
Section: Problem Formulationmentioning
confidence: 99%
“…If the environment is static, then risk contours can be generated offline. If the environment is highly dynamic, such as a traffic scene, and if the robot is an autonomous driving car with strong computing power, then the prediction module of the car predicts the future trajectories of surrounding vehicles at high frequency [26,27] and risk contours can be form at high frequency, too.…”
Section: F Theoretical Guarantees and Summarymentioning
confidence: 99%