arXiv research

Improved GFlowNets learn more efficiently with trajectory balance.

Variational inference improves training of generative flow networks.

Tracking large numbers of densely-arranged, interacting objects is challenging due to occlusions and the resulting complexity of possible trajectory combinations, as well as the sparsity of relevant, labeled datasets. Here we describe a novel technique of collective tracking in the model environment of a 2D honeybee hi…

End-to-end multi-object tracking learns object interactions.

Method estimates forces from agent trajectories to infer static obstacles.

Recently, clustering moving object trajectories kept gaining interest from both the data mining and machine learning communities. This problem, however, was studied mainly and extensively in the setting where moving objects can move freely on the euclidean space. In this paper, we study the problem of clustering trajec…

The tremendous growth of positioning technologies and GPS enabled devices has produced huge volumes of tracking data during the recent years. This source of information constitutes a rich input for data analytics processes, either offline (e.g. cluster analysis, hot motion discovery) or online (e.g. short-term forecast…

We present a novel clustering approach for moving object trajectories that are constrained by an underlying road network. The approach builds a similarity graph based on these trajectories then uses modularity-optimization hiearchical graph clustering to regroup trajectories with similar profiles. Our experimental stud…

CitySim dataset captures vehicle trajectories for safety research.

MPE models traffic trajectory data to predict next locations.

New method for predicting paths of unpredictable objects with high confidence.

New research suggests continual learning should focus on both optimization objective and optimization trajectory.

Pattern ensembling fills in missing or inaccurate trajectory data.

Trajectory segmentation is the process of subdividing a trajectory into parts either by grouping points similar with respect to some measure of interest, or by minimizing a global objective function. Here we present a novel online algorithm for segmentation and summary, based on point density along the trajectory, and …

A drone-based MOT algorithm tracks vehicles using neural network detections and TPMBM filter.

Stochastic gradient descent's long-term fluctuations are described by a diffusion limit.

Survey of deep learning methods for video multi-object tracking.

Trajectory-level supervision allows efficient offline reinforcement learning.

Representation learning of pedestrian trajectories transforms variable-length timestamp-coordinate tuples of a trajectory into a fixed-length vector representation that summarizes spatiotemporal characteristics. It is a crucial technique to connect feature-based data mining with trajectory data. Trajectory representati…

Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse. However, deciding when to stop optimizing and collect new trajectories is non-triv…

Proposes a model for generating survival trajectories and data.

Even though clustering trajectory data attracted considerable attention in the last few years, most of prior work assumed that moving objects can move freely in an euclidean space and did not consider the eventual presence of an underlying road network and its influence on evaluating the similarity between trajectories…

A new platform predicts object movements without needing specific context.

The paper improves model-based reinforcement learning by using multi-timestep objectives.

ELM combines machine learning and feature engineering for anomalous diffusion detection.

New method recovers diverse policies from expert data using state-action pair weighting.

In this work, we take a representation learning perspective on hierarchical reinforcement learning, where the problem of learning lower layers in a hierarchy is transformed into the problem of learning trajectory-level generative models. We show that we can learn continuous latent representations of trajectories, which…

DGFS improves sampling from complex densities by optimizing partial trajectories.

Geometric Brownian motion (GBM) is a key model for representing self-reproducing entities. Self-reproduction may be considered the definition of life [5], and the dynamics it induces are of interest to those concerned with living systems from biology to economics. Trajectories of GBM are distributed according to the we…

Trajectory-wise CVs reduce variance in policy gradient methods.

Study uses vehicle trajectory data to predict traffic incidents on highways.

Improving Bayesian filtering with strictly proper scoring rules

Unsupervised exploration and representation learning become increasingly important when learning in diverse and sparse environments. The information-theoretic principle of empowerment formalizes an unsupervised exploration objective through an agent trying to maximize its influence on the future states of its environme…

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biase…

A new framework uses stochastic optimal control to estimate rare events more accurately.

We propose a method to learn a distribution of shape trajectories from longitudinal data, i.e. the collection of individual objects repeatedly observed at multiple time-points. The method allows to compute an average spatiotemporal trajectory of shape changes at the group level, and the individual variations of this tr…

In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might be the most valuable for learning. In this paper, we develop an energy-based fr…

Bayesian methods improve tracking multiple objects through dynamic dependencies.

The paper introduces a new intrinsic reward method for exploration in reinforcement learning.

Generative model learns to mimic time-series behavior to generate accurate trajectories.

This paper explores a simple regularizer for reinforcement learning by proposing Generative Adversarial Self-Imitation Learning (GASIL), which encourages the agent to imitate past good trajectories via generative adversarial imitation learning framework. Instead of directly maximizing rewards, GASIL focuses on reproduc…

CCM improves context for Meta-RL by contrastive learning.

Paper proposes a method to learn goal-reaching behaviors from scratch using imitation learning.

Model predicts multi-agent trajectories using a differentiable simulator.

A common assumption in financial engineering is that the market price for any derivative coincides with an objectively defined risk-neutral price - a plausible assumption only if traders collectively possess objective knowledge about the price dynamics of the underlying security over short time scales. Here we assume t…

Bayesian Neural ODEs improve vessel trajectory prediction with better uncertainty estimates.

Paper proposes learning system dynamics from irregularly-sampled partial observations.

PODNet discovers plannable options from unstructured demonstrations.