PiP: Planning-informed Trajectory Prediction for Autonomous Driving

@article{Song2020PiPPT,
  title={PiP: Planning-informed Trajectory Prediction for Autonomous Driving},
  author={Haoran Song and Wenchao Ding and Yuxuan Chen and Shaojie Shen and Michael Yu Wang and Qifeng Chen},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.11476}
}
It is critical to predict the motion of surrounding vehicles for self-driving planning, especially in a socially compliant and flexible way. However, future prediction is challenging due to the interaction and uncertainty in driving behaviors. We propose planning-informed trajectory prediction (PiP) to tackle the prediction problem in the multi-agent setting. Our approach is differentiated from the traditional manner of prediction, which is only based on historical information and decoupled… 
A Survey on Deep-Learning Approaches for Vehicle Trajectory Prediction in Autonomous Driving
TLDR
This work reviews and categorizes existing learning-based trajectory forecasting methods from perspectives of representation, modeling, and learning, and makes the implementation of Target-driveN Trajectory Prediction publicly available at https://github.com/ Henry1iu/TNT-Trajectory-Predition, demonstrating its outstanding performance whereas its original codes are withheld.
Maneuver-based Trajectory Prediction for Self-driving Cars Using Spatio-temporal Convolutional Networks
TLDR
A new, datadriven approach for predicting the motion of vehicles in a road environment that jointly exploits correlations in the spatial and temporal domain using convolutional neural networks and is able to achieve a competitive prediction performance.
A Novel Graph based Trajectory Predictor with Pseudo Oracle
TLDR
The Graph-based Trajectory Predictor with Pseudo-Oracle (GTPPO), an encoder-decoder-based method conditioned on pedestrians' future behaviors, which is evaluated on ETH, UCY, and Stanford Drone datasets, and the results demonstrate state-of-the-art performance.
B-GAP: Behavior-Guided Action Prediction and Navigation for Autonomous Driving.
TLDR
An algorithm for behaviorally-guided action prediction and local navigation for autonomous driving in dense traffic scenarios, and a behavior-driven simulator that can generate trajectories corresponding to different levels of aggressive behaviors, is presented.
Deep Structured Reactive Planning
TLDR
This paper proposes a novel data-driven, reactive planning objective which allows a self-driving vehicle to jointly reason about its own plans as well as how other actors will react to them and demonstrates that the reactive model outperforms a non-reactive variant in successfully completing highly complex maneuvers faster, without trading off collision rate.
EPSILON: An Efficient Planning System for Automated Vehicles in Highly Interactive Environments
  • Wenchao Ding, Lu Zhang, Jing Chen, Shaojie Shen
  • Computer Science
    IEEE Transactions on Robotics
  • 2021
TLDR
EPSILON is an efficient interactionaware planning system for automated driving that achieves human-like driving behaviors in highly interactive traffic flow smoothly and safely without being over-conservative compared to the existing planning methods.
End-to-End Interactive Prediction and Planning with Optical Flow Distillation for Autonomous Driving
TLDR
This paper proposes an end-to-end interactive neural motion planner (INMP) for autonomous driving that first generates a feature map in bird’s-eyeview space, which is then processed to detect other agents and perform interactive prediction and planning jointly.
Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers
TLDR
This work proposes Euro-PVI, a dataset of pedestrian and bicyclist trajectories that caters more diverse and complex interactions in dense urban scenarios compared to the existing datasets and develops a joint inference model that learns an expressive multi-modal shared latent space across agents in the urban scene.
Grounding Linguistic Commands to Navigable Regions
TLDR
This work proposes the novel task of Referring Navigable Regions (RNR), i.e., grounding regions of interest for navigation based on the linguistic command, and introduces a new dataset, Talk2Car-RegSeg, which extends the existing Talk2car dataset with segmentation masks for the regions described by the linguistic commands.
...
1
2
...

References

SHOWING 1-10 OF 37 REFERENCES
Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning
  • Liting Sun, W. Zhan, M. Tomizuka
  • Computer Science, Mathematics
    2018 21st International Conference on Intelligent Transportation Systems (ITSC)
  • 2018
TLDR
The quantitative results show that the proposed approach can accurately predict both the discrete driving decisions such as yield or pass as well as the continuous trajectories.
Towards a Fatality-Aware Benchmark of Probabilistic Reaction Prediction in Highly Interactive Driving Scenarios
TLDR
A probabilistic reaction prediction problem is formulated, the relationship between reaction and situation prediction problems are revealed, and a fatality-aware metric is proposed, which is a weighted Brier score based on the criticality of the trajectory pairs of the interacting entities.
PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings
TLDR
A probabilistic forecasting model of future interactions between a variable number of agents that performs both standard forecasting and the novel task of conditional forecasting, which reasons about how all agents will likely respond to the goal of a controlled agent.
Optimal trajectory generation for dynamic street scenarios in a Frenét Frame
TLDR
A semi-reactive trajectory generation method, which can be tightly integrated into the behavioral layer of the holistic autonomous system, that realizes long-term objectives such as velocity keeping, merging, following, stopping, in combination with a reactive collision avoidance by means of optimal-control strategies within the Frenét-Frame of the street.
TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents
TLDR
The proposed long short-term memory-based (LSTM-based) realtime traffic prediction algorithm, TrafficPredict, uses an instance layer to learn instances' movements and interactions and has a category layer to learning the similarities of instances belonging to the same type to refine the prediction.
Motion planning for autonomous driving with a conformal spatiotemporal lattice
TLDR
A search space representation is presented that allows the search algorithm to systematically and efficiently explore both spatial and temporal dimensions in real time and allows the low-level trajectory planner to assume greater responsibility in planning to follow a leading vehicle, perform lane changes, and merge between other vehicles.
A Belief State Planner for Interactive Merge Maneuvers in Congested Traffic
TLDR
A novel motion model representing the uncertain cooperation of other drivers is presented based on a logistic regression model estimating the probability for cooperative behavior of a human driver given a future scene.
Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
  • Tianyang Zhao, Yifei Xu, +5 authors Y. Wu
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
TLDR
This work encodes multiple agents' past trajectories and the scene context into a Multi-Agent Tensor, then applies convolutional fusion to capture multiagent interactions while retaining the spatial structure of agents and thescene context.
Predicting Vehicle Behaviors Over An Extended Horizon Using Behavior Interaction Network
TLDR
This paper uncovers that clues to vehicle behaviors over an extended horizon can be found in vehicle interaction, which makes it possible to anticipate the likelihood of a certain behavior, even in the absence of any clear maneuver pattern.
Baidu Apollo EM Motion Planner
TLDR
A real-time motion planning system based on the Baidu Apollo (open source) autonomous driving platform that aims to address the industrial level-4 motion planning problem while considering safety, comfort and scalability is introduced.
...
1
2
3
4
...