arXiv research

Paper uses deep imitation learning to predict aircraft trajectories accurately.

Generative model learns vehicle trajectory distributions for better data generalization.

Analyzing the urban trajectory in cities has become an important topic in data mining. How can we model the human mobility consisting of stay and travel from the raw trajectory data? How can we infer such a mobility model from the single trajectory information? How can we further generalize the mobility inference to ac…

Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. In such problems, the way we choose to represent a trajectory underlies algorithms for trajectory prediction and optimization. Interestingly, most all prior work in imitation and reinforcemen…

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…

A new reinforcement learning method reduces action complexity for robust control.

Algorithm learns mixtures of Markov chains and MDPs from short trajectories.

DETECT clusters mobility behaviors from trajectories using deep learning.

SafeMIL learns safer policies by avoiding risky behavior from non-preferred trajectories.

In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known. Generating smooth, dynamically feasible trajectories could be difficult for such sy…

Deep Reinforcement Learning has shown tremendous success in solving several games and tasks in robotics. However, unlike humans, it generally requires a lot of training instances. Trajectories imitating to solve the task at hand can help to increase sample-efficiency of deep RL methods. In this paper, we present a simp…

Enhances reinforcement learning from sparse data.

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…

New method learns behavioral representations from mobility data.

Paper proposes transferring neural network learning trajectories.

Trajectory optimization using a learned model of the environment is one of the core elements of model-based reinforcement learning. This procedure often suffers from exploiting inaccuracies of the learned model. We propose to regularize trajectory optimization by means of a denoising autoencoder that is trained on the …

Reinforcement learning with trajectory feedback instead of state-action rewards.

Study learns dynamics of linear systems from multiple short trajectories.

Study of supervised learning from multiple non-independent sequences.

Analyzing the temporal behavior of nodes in time-varying graphs is useful for many applications such as targeted advertising, community evolution and outlier detection. In this paper, we present a novel approach, STWalk, for learning trajectory representations of nodes in temporal graphs. The proposed framework makes u…

Gaussian process model learns Hamiltonian systems from noisy data.

New method improves learning from multiple correlated data trajectories.

Bayesian method estimates dynamics from near-optimal trajectories.

Paper characterizes optimal learning trajectories for high-dimensional nonlinear models.

We present a method for learning options from segmented demonstration trajectories. The trajectories are first segmented into skills using nonparametric Bayesian clustering and a reward function for each segment is then learned using inverse reinforcement learning. From this, a set of inferred trajectories for the demo…

Improved GFlowNets learn more efficiently with trajectory balance.

Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples. In such cases, using a set of expert trajectories could help to learn faster. However, Imitation Learning (IL) via supervised pre-training with these trajectories may not perform as well and gen…

LSS learns molecular trajectories from MD data.

Study benchmarks methods for learning non-Cartesian k-space trajectories and reconstruction.

Framework learns continuous dynamics from sparse trajectories.

KEMP predicts long-term trajectories for autonomous driving using keyframes.

The goal of this paper is to present a method for simultaneous trajectory and local stabilizing policy optimization to generate local policies for trajectory-centric model-based reinforcement learning (MBRL). This is motivated by the fact that global policy optimization for non-linear systems could be a very challengin…

DGFS improves sampling from complex densities by optimizing partial trajectories.

End-to-end model predicts multiagent trajectories using game theory and neural nets.

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

Visual observations of dynamic phenomena, such as human actions, are often represented as sequences of smoothly-varying features . In cases where the feature spaces can be structured as Riemannian manifolds, the corresponding representations become trajectories on manifolds. Analysis of these trajectories is challengin…

Generative model for SSc disease trajectories using deep learning.

Enhanced decision-making through Dreamer's anticipatory trajectories and Online Decision Transformer.

We address the problem of abnormal event detection from trajectory data. In this paper, a new adversarial approach is proposed for building a deep neural network binary classifier, trained in an unsupervised fashion, that can distinguish normal from abnormal trajectory-based events without the need for setting manual d…

Improved trajectory prediction for team sports using sparse outputs.

WS-II algorithm segments trajectories with high accuracy.

Trajectory-level supervision allows efficient offline reinforcement learning.

Meta-learning improves drone trajectory design for dynamic wireless networks.

Method predicts NBA players' multi-modal movement trajectories.

This paper compares deep learning and knowledge-based methods for pedestrian trajectory prediction.

Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires access to demonstrations from a human supervisor. In this paper, we study…

MOCK learns complex systems from trajectories efficiently.

Safe active learning for time-series models with Gaussian processes.