HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Sampling

  title={HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Sampling},
  author={Xin Huang and Guy Rosman and Igor Gilitschenski and Ashkan M. Z. Jasour and Stephen G. McGill and John J. Leonard and Brian Charles Williams},
  journal={2022 International Conference on Robotics and Automation (ICRA)},
  • Xin HuangG. Rosman B. Williams
  • Published 5 October 2021
  • Computer Science
  • 2022 International Conference on Robotics and Automation (ICRA)
Modeling multi-modal high-level intent is important for ensuring diversity in trajectory prediction. Existing approaches explore the discrete nature of human intent before predicting continuous trajectories, to improve accuracy and support explainability. However, these approaches often assume the intent to remain fixed over the prediction horizon, which is problematic in practice, especially over longer horizons. To overcome this limitation, we introduce HYPER, a general and expressive hybrid… 

Figures and Tables from this paper

M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction

This work exploits the underlying relations between interacting agents and decouple the joint prediction problem into marginal prediction problems, and first classifies interacting agents as pairs of influencer and reactors, and then leverages a marginal prediction model and a conditional prediction model to predict trajectories for the influencers and reactors.

TIP: Task-Informed Motion Prediction for Intelligent Vehicles

This paper proposes a task-informed motion prediction model that better supports the tasks through its predictions by jointly reasoning about prediction accuracy and the utility of the downstream tasks during training, in the context of autonomous driving and parallel autonomy.

Trajectory Prediction with Linguistic Representations

A novel trajectory prediction model that uses linguistic intermediate representations to forecast trajectories, and is trained using trajectory samples with partially-annotated captions, which can aid model development and can aid in building confidence in the model before deploying it.

Safe, Learning-Based MPC for Highway Driving under Lane-Change Uncertainty: A Distributionally Robust Approach

We present a case study applying learning-based distributionally robust model predictive control to highway motion planning under stochastic uncertainty of the lane change behavior of surrounding

SUPR-GAN: SUrgical PRediction GAN for Event Anticipation in Laparoscopic and Robotic Surgery

This work uses a novel Generative Adversarial Network (GAN) formulation to sample future surgical phases trajectories conditioned on past video frames from laparoscopic cholecystectomy (LC) videos and compares it to state-of-the-art approaches for surgical video analysis and alternative prediction methods.

MPA: MultiPath++ Based Architecture for Motion Prediction

This work presents one of the solutions for Waymo Motion Prediction Challenge 2022 based on MultiPath++, ranked the 3rd as of May, 26 2022.

Benchmark for Models Predicting Human Behavior in Gap Acceptance Scenarios

This work develops a framework facilitating the evaluation of any model, by any metric, and in any scenario, and applies it to state-of-the-art prediction models, which all show themselves to be unreliable in the most safety- critical situations.

InterSim: Interactive Traffic Simulation via Explicit Relation Modeling

This work presents InterSim, an interactive traffic simulator for testing autonomous driving planners, which achieves better simulation realism and reactivity in two simulation tasks compared to a state-of-the-art learning-based traffic simulator.

VectorFlow: Combining Images and Vectors for Traffic Occupancy and Flow Prediction

This work proposes a novel occupancy flow fields predictor, by combining the power of an image encoder that learns features from a rasterized traffic image and a vector encoding that captures information of continuous agent trajectories and map states, which achieves the best performance in the occluded occupancy and prediction task.



MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction

This work presents MultiPath, which leverages a fixed set of future state-sequence anchors that correspond to modes of the trajectory distribution, which is efficient, requiring only one forward inference pass to obtain multi-modal future distributions, and the output is parametric, allowing compact communication and analytical probabilistic queries.

PTP: Parallelized Tracking and Prediction With Graph Neural Networks and Diversity Sampling

This work proposes a parallelized framework for tracking and prediction sequentially which can propagate errors from tracking to prediction, and uses a diversity sampling function to improve the quality and diversity of the authors' forecasted trajectories.

TNT: Target-driveN Trajectory Prediction

The key insight is that for prediction within a moderate time horizon, the future modes can be effectively captured by a set of target states, which leads to the target-driven trajectory prediction (TNT) framework.

Diverse Trajectory Forecasting with Determinantal Point Processes

This work proposes to learn a diversity sampling function (DSF) that generates a diverse and likely set of future trajectories and demonstrates the diversity of the trajectories produced by the approach on both low-dimensional 2D trajectory data and high-dimensional human motion data.

DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling

This work first extends the generative adversarial network framework with a low-dimensional approximate semantic space, and shape that space to capture semantics such as merging and turning, and sample from this space in a way that mimics the predicted distribution, but allows us to control coverage of semantically distinct outcomes.

Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction

This work presents an approach that involves the prediction of several samples of the future with a winner-takes-all loss and iterative grouping of samples to multiple modes and shows on synthetic and real data that the proposed approach triggers good estimates of multimodal distributions and avoids mode collapse.

From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting

Y-net is presented, a scene compliant trajectory forecasting network that exploits the proposed epistemic and aleatoric structure for diverse trajectory predictions across long prediction horizons and proposes a novel long term trajectory forecasting setting.

Learning to Predict Vehicle Trajectories with Model-based Planning

This paper introduces a novel prediction framework called PRIME, which stands for Prediction with Model-based Planning, which outperforms the state-of-the-art methods in prediction accuracy, feasibility, and robustness under imperfect tracking.

CoverNet: Multimodal Behavior Prediction Using Trajectory Sets

CoverNet is presented, a new method for multimodal, probabilistic trajectory prediction for urban driving that demonstrates its approach on public, real world self-driving datasets, and shows that it outperforms state-of-the-art methods.

Analyzing the Variety Loss in the Context of Probabilistic Trajectory Prediction

  • L. ThiedeP. Brahma
  • Computer Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
This work presents a proof to show that the MoN loss does not lead to the ground truth probability density function, but approximately to its square root instead.