Motion Manifold Flow Primitives for Task-Conditioned Trajectory Generation under Complex Task-Motion Dependencies
- URL: http://arxiv.org/abs/2407.19681v3
- Date: Wed, 08 Jan 2025 06:56:19 GMT
- Title: Motion Manifold Flow Primitives for Task-Conditioned Trajectory Generation under Complex Task-Motion Dependencies
- Authors: Yonghyeon Lee, Byeongho Lee, Seungyeon Kim, Frank C. Park,
- Abstract summary: Motion Manifold Flow Primitives is a framework that decouples the training of the motion manifold from taskconditioned distributions.
We employ flow matching models, state-of-the-art conditional deep generative models, to learn task-conditioned distributions.
Experiments are conducted on language-guided trajectory generation tasks, where many-to-many text-motion correspondences introduce complex task-motion dependencies.
- Score: 13.422270806078924
- License:
- Abstract: Effective movement primitives should be capable of encoding and generating a rich repertoire of trajectories -- typically collected from human demonstrations -- conditioned on task-defining parameters such as vision or language inputs. While recent methods based on the motion manifold hypothesis, which assumes that a set of trajectories lies on a lower-dimensional nonlinear subspace, address challenges such as limited dataset size and the high dimensionality of trajectory data, they often struggle to capture complex task-motion dependencies, i.e., when motion distributions shift drastically with task variations. To address this, we introduce Motion Manifold Flow Primitives (MMFP), a framework that decouples the training of the motion manifold from task-conditioned distributions. Specifically, we employ flow matching models, state-of-the-art conditional deep generative models, to learn task-conditioned distributions in the latent coordinate space of the learned motion manifold. Experiments are conducted on language-guided trajectory generation tasks, where many-to-many text-motion correspondences introduce complex task-motion dependencies, highlighting MMFP's superiority over existing methods.
Related papers
- One Fits All: General Mobility Trajectory Modeling via Masked Conditional Diffusion [11.373845190033297]
Trajectory data play a crucial role in many applications, ranging from network optimization to urban planning.
Existing studies on trajectory data are task-specific, and their applicability is limited to the specific tasks on which they have been trained, such as generation, recovery, or prediction.
We propose a general trajectory modeling framework via conditional diffusion (named GenMove)
Our model significantly outperforms state-of-the-art baselines, with the highest performance exceeding 13% improvement in generation tasks.
arXiv Detail & Related papers (2025-01-23T03:13:45Z) - Multi-Agent Path Finding in Continuous Spaces with Projected Diffusion Models [57.45019514036948]
Multi-Agent Path Finding (MAPF) is a fundamental problem in robotics.
This work proposes a novel approach that integrates constrained optimization with diffusion models for MAPF in continuous spaces.
arXiv Detail & Related papers (2024-12-23T21:27:19Z) - DeTra: A Unified Model for Object Detection and Trajectory Forecasting [68.85128937305697]
Our approach formulates the union of the two tasks as a trajectory refinement problem.
To tackle this unified task, we design a refinement transformer that infers the presence, pose, and multi-modal future behaviors of objects.
In our experiments, we observe that ourmodel outperforms the state-of-the-art on Argoverse 2 Sensor and Open dataset.
arXiv Detail & Related papers (2024-06-06T18:12:04Z) - Task Indicating Transformer for Task-conditional Dense Predictions [16.92067246179703]
We introduce a novel task-conditional framework called Task Indicating Transformer (TIT) to tackle this challenge.
Our approach designs a Mix Task Adapter module within the transformer block, which incorporates a Task Indicating Matrix through matrix decomposition.
We also propose a Task Gate Decoder module that harnesses a Task Indicating Vector and gating mechanism to facilitate adaptive multi-scale feature refinement.
arXiv Detail & Related papers (2024-03-01T07:06:57Z) - DiverseMotion: Towards Diverse Human Motion Generation via Discrete
Diffusion [70.33381660741861]
We present DiverseMotion, a new approach for synthesizing high-quality human motions conditioned on textual descriptions.
We show that our DiverseMotion achieves the state-of-the-art motion quality and competitive motion diversity.
arXiv Detail & Related papers (2023-09-04T05:43:48Z) - Curriculum Modeling the Dependence among Targets with Multi-task
Learning for Financial Marketing [26.80709680959278]
We propose a prior information merged model (textbfPIMM) for multiple sequential dependence task learning.
The PIM randomly selects the true label information or the prior task prediction with a soft sampling strategy to transfer to the downstream task during the training.
The offline experimental results on both public and product datasets verify that PIMM outperforms state-of-the-art baselines.
arXiv Detail & Related papers (2023-04-25T07:55:16Z) - Executing your Commands via Motion Diffusion in Latent Space [51.64652463205012]
We propose a Motion Latent-based Diffusion model (MLD) to produce vivid motion sequences conforming to the given conditional inputs.
Our MLD achieves significant improvements over the state-of-the-art methods among extensive human motion generation tasks.
arXiv Detail & Related papers (2022-12-08T03:07:00Z) - STGlow: A Flow-based Generative Framework with Dual Graphormer for
Pedestrian Trajectory Prediction [22.553356096143734]
We propose a novel generative flow based framework with dual graphormer for pedestrian trajectory prediction (STGlow)
Our method can more precisely model the underlying data distribution by optimizing the exact log-likelihood of motion behaviors.
Experimental results on several benchmarks demonstrate that our method achieves much better performance compared to previous state-of-the-art approaches.
arXiv Detail & Related papers (2022-11-21T07:29:24Z) - MoDi: Unconditional Motion Synthesis from Diverse Data [51.676055380546494]
We present MoDi, an unconditional generative model that synthesizes diverse motions.
Our model is trained in a completely unsupervised setting from a diverse, unstructured and unlabeled motion dataset.
We show that despite the lack of any structure in the dataset, the latent space can be semantically clustered.
arXiv Detail & Related papers (2022-06-16T09:06:25Z) - Learning to Shift Attention for Motion Generation [55.61994201686024]
One challenge of motion generation using robot learning from demonstration techniques is that human demonstrations follow a distribution with multiple modes for one task query.
Previous approaches fail to capture all modes or tend to average modes of the demonstrations and thus generate invalid trajectories.
We propose a motion generation model with extrapolation ability to overcome this problem.
arXiv Detail & Related papers (2021-02-24T09:07:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.