skip to main content

Title: Trajectory prediction with latent belief energy-based model
Human trajectory prediction is critical for autonomous platforms like self-driving cars or social robots. We present a latent belief energy-based model (LB-EBM) for diverse human trajectory forecast. LB-EBM is a probabilistic model with cost function defined in the latent space to account for the movement history and social context. The low dimensionality of the latent space and the high expressivity of the EBM make it easy for the model to capture the multimodality of pedestrian trajectory distributions. LB-EBM is learned from expert demonstrations (i.e., human trajectories) projected into the latent space. Sampling from or optimizing the learned LB-EBM yields a belief vector which is used to make a path plan, which then in turn helps to predict a long-range trajectory. The effectiveness of LB-EBM and the two-step approach are supported by strong empirical results. Our model is able to make accurate, multi-modal, and social compliant trajectory predictions and improves over prior state-of-the-arts performance on the Stanford Drone trajectory prediction benchmark by 10:9% and on the ETH-UCY benchmark by 27:6%.
; ; ;
Award ID(s):
Publication Date:
Journal Name:
IEEE Conference on Computer Vision and Pattern Recognition
Sponsoring Org:
National Science Foundation
More Like this
  1. We propose to learn energy-based model (EBM) in the latent space of a generator model, so that the EBM serves as a prior model that stands on the top-down networkofthegeneratormodel. BoththelatentspaceEBMandthetop-down network can be learned jointly by maximum likelihood, which involves short-run MCMC sampling from both the prior and posterior distributions of the latent vector. Due to the low dimensionality of the latent space and the expressiveness of the top-down network, a simple EBM in latent space can capture regularities in the data effectively, and MCMC sampling in latent space is efficient and mixes well. We show that the learned model exhibits strong performances in terms of image and text generation and anomaly detection. The one-page code can be found in supplementary materials.
  2. Learning energy-based model (EBM) requires MCMC sampling of the learned model as an inner loop of the learning algorithm. However, MCMC sampling of EBMs in high-dimensional data space is generally not mixing, because the energy function, which is usually parametrized by deep network, is highly multi-modal in the data space. This is a serious handicap for both theory and practice of EBMs. In this paper, we propose to learn EBM with a flow-based model (or in general latent variable model) serving as a backbone, so that the EBM is a correction or an exponential tilting of the flow-based model. We show that the model has a particularly simple form in the space of the latent variables of the generative model, and MCMC sampling of the EBM in the latent space mixes well and traverses modes in the data space. This enables proper sampling and learning of EBMs.
  3. Ocean ecosystems have spatiotemporal variability and dynamic complexity that require a long-term deployment of an autonomous underwater vehicle for data collection. A new generation of long-range autonomous underwater vehicles (LRAUVs), such as the Slocum glider and Tethys-class AUV, has emerged with high endurance, long-range, and energy-aware capabilities. These new vehicles provide an effective solution to study different oceanic phenomena across multiple spatial and temporal scales. For these vehicles, the ocean environment has forces and moments from changing water currents which are generally on the order of magnitude of the operational vehicle velocity. Therefore, it is not practical to generate a simple trajectory from an initial location to a goal location in an uncertain ocean, as the vehicle can deviate significantly from the prescribed trajectory due to disturbances resulted from water currents. Since state estimation remains challenging in underwater conditions, feedback planning must incorporate state uncertainty that can be framed into a stochastic energy-aware path planning problem. This article presents an energy-aware feedback planning method for an LRAUV utilizing its kinematic model in an underwater environment under motion and sensor uncertainties. Our method uses ocean dynamics from a predictive ocean model to understand the water flow pattern and introduces a goal-constrainedmore »belief space to make the feedback plan synthesis computationally tractable. Energy-aware feedback plans for different water current layers are synthesized through sampling and ocean dynamics. The synthesized feedback plans provide strategies for the vehicle that drive it from an environment’s initial location toward the goal location. We validate our method through extensive simulations involving the Tethys vehicle’s kinematic model and incorporating actual ocean model prediction data.« less
  4. Cooperatively avoiding collision is a critical functionality for robots navigating in dense human crowds, failure of which could lead to either overaggressive or overcautious behavior. A necessary condition for cooperative collision avoidance is to couple the prediction of the agents’ trajectories with the planning of the robot’s trajectory. However, it is unclear that trajectory based cooperative collision avoidance captures the correct agent attributes. In this work we migrate from trajectory based coupling to a formalism that couples agent preference distributions. In particular, we show that preference distributions (probability density functions representing agents’ intentions) can capture higher order statistics of agent behaviors, such as willingness to cooperate. Thus, coupling in distribution space exploits more information about inter-agent cooperation than coupling in trajectory space. We thus introduce a general objective for coupled prediction and planning in distribution space, and propose an iterative best response optimization method based on variational analysis with guaranteed sufficient decrease. Based on this analysis, we develop a sampling-based motion planning framework called DistNav1 that runs in real time on a laptop CPU. We evaluate our approach on challenging scenarios from both real world datasets and simulation environments, and benchmark against a wide variety of model based and machinemore »learning based approaches. The safety and efficiency statistics of our approach outperform all other models. Finally, we find that DistNav is competitive with human safety and efficiency performance.« less
  5. This paper studies the problem of predicting the distribution over multiple possible future paths of people as they move through various visual scenes. We make two main contributions. The first contribution is a new dataset, created in a realistic 3D simulator, which is based on real world trajectory data, and then extrapolated by human annotators to achieve different latent goals. This provides the first benchmark for quantitative evaluation of the models to predict multi-future trajectories. The second contribution is a new model to generate multiple plausible future trajectories, which contains novel designs of using multi-scale location encodings and convolutional RNNs over graphs. We refer to our model as Multiverse. We show that our model achieves the best results on our dataset, as well as on the real-world VIRAT/ActEV dataset (which just contains one possible future).