Related papers: MetaTra: Meta-Learning for Generalized Trajectory …

Most pedestrian trajectory prediction methods rely on a huge amount of trajectories annotation, which is time-consuming and expensive. Moreover, a well-trained model may not effectively generalize to a new scenario captured by another…

Meta learning is a promising technique for solving few-shot fault prediction problems, which have attracted the attention of many researchers in recent years. Existing meta-learning methods for time series prediction, which predominantly…

Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving. Given the heavy reliance of current trajectory forecasting models on data-driven methodologies, we aim…

Volume prediction is one of the fundamental objectives in the Fintech area, which is helpful for many downstream tasks, e.g., algorithmic trading. Previous methods mostly learn a universal model for different stocks. However, this kind of…

Model-based reinforcement learning (RL) has shown great potential in various control tasks in terms of both sample-efficiency and final performance. However, learning a generalizable dynamics model robust to changes in dynamics remains a…

Autonomous mobile robots require accurate human motion predictions to safely and efficiently navigate among pedestrians, whose behavior may adapt to environmental changes. This paper introduces a self-supervised continual learning framework…

A reliable long-term time-series forecaster is highly demanded in practice but comes across many challenges such as low computational and memory footprints as well as robustness against dynamic learning environments. This paper proposes…

Over the past decade, deep neural networks have demonstrated significant success using the training scheme that involves mini-batch stochastic gradient descent on extensive datasets. Expanding upon this accomplishment, there has been a…

Multi-object tracking (MOT) and trajectory prediction are two critical components in modern 3D perception systems that require accurate modeling of multi-agent interaction. We hypothesize that it is beneficial to unify both tasks under one…

With the advancements of sensor hardware, traffic infrastructure and deep learning architectures, trajectory prediction of vehicles has established a solid foundation in intelligent transportation systems. However, existing solutions are…

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns…

Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains). Existing methods focus on expanding the distribution of the training domain to…

We introduce Masked Trajectory Models (MTM) as a generic abstraction for sequential decision making. MTM takes a trajectory, such as a state-action sequence, and aims to reconstruct the trajectory conditioned on random subsets of the same…

As robots across domains start collaborating with humans in shared environments, algorithms that enable them to reason over human intent are important to achieve safe interplay. In our work, we study human intent through the problem of…

Many real-world domains are subject to a structured non-stationarity which affects the agent's goals and the environmental dynamics. Meta-reinforcement learning (RL) has been shown successful for training agents that quickly adapt to…

Multitarget Tracking (MTT) is the problem of tracking the states of an unknown number of objects using noisy measurements, with important applications to autonomous driving, surveillance, robotics, and others. In the model-based Bayesian…

As a subset of machine learning, meta-learning, or learning to learn, aims at improving the model's capabilities by employing prior knowledge and experience. A meta-learning paradigm can appropriately tackle the conventional challenges of…

Predicting pedestrian motion trajectories is crucial for path planning and motion control of autonomous vehicles. Accurately forecasting crowd trajectories is challenging due to the uncertain nature of human motions in different…

The single domain generalization(SDG) based on meta-learning has emerged as an effective technique for solving the domain-shift problem. However, the inadequate match of data distribution between source and augmented domains and difficult…

In real-world applications, deep learning models often run in non-stationary environments where the target data distribution continually shifts over time. There have been numerous domain adaptation (DA) methods in both online and offline…