Related papers: Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree

Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree

URL: http://arxiv.org/abs/2405.17879v2
Date: Fri, 7 Jun 2024 12:27:03 GMT
Title: Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree
Authors: Lang Feng, Pengjie Gu, Bo An, Gang Pan,
Abstract summary: Trajectory Aggregation Tree (TAT) is a dynamic tree-like structure based on historical and current trajectories. TAT can be deployed without modifying the original training and sampling pipelines of diffusion planners, making it a training-free, ready-to-deploy solution. Our results highlight its remarkable ability to resist the risk from unreliable trajectories, guarantee the performance boosting of diffusion planners in $100%$ of tasks, and exhibit an appreciable tolerance margin for sample quality, thereby enabling planning with a more than $3times$ acceleration.
Score: 20.855596726996712
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Diffusion planners have shown promise in handling long-horizon and sparse-reward tasks due to the non-autoregressive plan generation. However, their inherent stochastic risk of generating infeasible trajectories presents significant challenges to their reliability and stability. We introduce a novel approach, the Trajectory Aggregation Tree (TAT), to address this issue in diffusion planners. Compared to prior methods that rely solely on raw trajectory predictions, TAT aggregates information from both historical and current trajectories, forming a dynamic tree-like structure. Each trajectory is conceptualized as a branch and individual states as nodes. As the structure evolves with the integration of new trajectories, unreliable states are marginalized, and the most impactful nodes are prioritized for decision-making. TAT can be deployed without modifying the original training and sampling pipelines of diffusion planners, making it a training-free, ready-to-deploy solution. We provide both theoretical analysis and empirical evidence to support TAT's effectiveness. Our results highlight its remarkable ability to resist the risk from unreliable trajectories, guarantee the performance boosting of diffusion planners in $100\%$ of tasks, and exhibit an appreciable tolerance margin for sample quality, thereby enabling planning with a more than $3\times$ acceleration.

Related papers

TrajDiffuse: A Conditional Diffusion Model for Environment-Aware Trajectory Prediction [16.188078087197106]
We propose TrajDiffuse, a planning-based trajectory prediction method using a novel guided conditional diffusion model. We form the trajectory prediction problem as a denoising impaint task and design a map-based guidance term for the diffusion process. TrajDiffuse is able to generate trajectory predictions that match or exceed the accuracy and diversity of the SOTA, while adhering almost perfectly to environmental constraints.
arXiv Detail & Related papers (2024-10-14T17:59:03Z)
Rejection via Learning Density Ratios [50.91522897152437]
Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance. Our framework is tested empirically over clean and noisy datasets.
arXiv Detail & Related papers (2024-05-29T01:32:17Z)
Certified Human Trajectory Prediction [66.1736456453465]
Tray prediction plays an essential role in autonomous vehicles. We propose a certification approach tailored for the task of trajectory prediction. We address the inherent challenges associated with trajectory prediction, including unbounded outputs, and mutli-modality.
arXiv Detail & Related papers (2024-03-20T17:41:35Z)
Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference [53.419249906014194]
We study generative modeling for planning with datasets repurposed from offline reinforcement learning. We introduce the Latent Plan Transformer (), a novel model that leverages a latent variable to connect a Transformer-based trajectory generator and the final return.
arXiv Detail & Related papers (2024-02-07T08:18:09Z)
EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomy [34.19779754333234]
This work proposes a unified framework to learn uncertainty-aware traction model and plan risk-aware trajectories. We parameterize Dirichlet distributions with the network outputs and propose a novel uncertainty-aware squared Earth Mover's distance loss. Our approach is extensively validated in simulation and on wheeled and quadruped robots.
arXiv Detail & Related papers (2023-11-10T18:49:53Z)
Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans [25.326624139426514]
Diffusion-based planning has shown promising results in long-horizon, sparse-reward tasks. However, due to their nature as generative models, diffusion models are not guaranteed to generate feasible plans. We propose a novel approach to refine unreliable plans generated by diffusion models by providing refining guidance to error-prone plans.
arXiv Detail & Related papers (2023-10-30T10:35:42Z)
SafeDiffuser: Safe Planning with Diffusion Probabilistic Models [97.80042457099718]
Diffusion model-based approaches have shown promise in data-driven planning, but there are no safety guarantees. We propose a new method, called SafeDiffuser, to ensure diffusion probabilistic models satisfy specifications. We test our method on a series of safe planning tasks, including maze path generation, legged robot locomotion, and 3D space manipulation.
arXiv Detail & Related papers (2023-05-31T19:38:12Z)
Risk-aware Path Planning via Probabilistic Fusion of Traversability Prediction for Planetary Rovers on Heterogeneous Terrains [11.060425537315087]
We propose a new path planning algorithm that explicitly accounts for erroneous traversability prediction. The proposed method is able to generate more feasible paths on heterogeneous terrains compared to existing methods.
arXiv Detail & Related papers (2023-03-02T11:19:44Z)
Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models [37.09462631862042]
Reasoning with occluded traffic agents is a significant open challenge for planning for autonomous vehicles. Recent deep learning models have shown impressive results for predicting occluded agents based on the behaviour of nearby visible agents. We propose Bi-level Variational Occlusion Models (BiVO), a two-step generative model that first predicts likely locations of occluded agents, and then generates likely trajectories for the occluded agents.
arXiv Detail & Related papers (2022-10-26T09:39:31Z)
Trajectory Forecasting from Detection with Uncertainty-Aware Motion Encoding [121.66374635092097]
Trajectories obtained from object detection and tracking are inevitably noisy. We propose a trajectory predictor directly based on detection results without relying on explicitly formed trajectories.
arXiv Detail & Related papers (2022-02-03T09:09:56Z)
From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting [54.273455592965355]
Uncertainty in future trajectories stems from two sources: (a) sources known to the agent but unknown to the model, such as long term goals and (b)sources that are unknown to both the agent & the model, such as intent of other agents & irreducible randomness indecisions. We model the epistemic un-certainty through multimodality in long term goals and the aleatoric uncertainty through multimodality in waypoints& paths. To exemplify this dichotomy, we also propose a novel long term trajectory forecasting setting, with prediction horizons upto a minute, an order of magnitude longer than prior works.
arXiv Detail & Related papers (2020-12-02T21:01:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.