arXiv subjects

Boshu Lei

Publications and source records attributed to Boshu Lei.

11 recordsLinked to original sources

arXiv2026

Reinforcement Learning for Flow-Matching Policies with Density Transport

We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems. Our key insight is to view RL-based policy improvement as a transport of action densities towards regions of high reward, which naturally aligns with the transport formulation of flow matching models. Prior methods either approximate the current or optimal policy distribution or resort to distillation, which introduces biased gradients or sacrifices multimodal modeling capacity. In contrast, our approach for RL with Density Transport, which we name \emph{RLDT}, constructs a transport field from a maximum-entropy RL objective using Stein Variational Gradient Descent (SVGD). Then, it finetunes a pretrained flow matching policy to align with this field. Training with this alignment objective is nontrivial because flow-matching policies generate actions via a multi-step process, making direct gradient-based optimization challenging. To overcome this challenge and stabilize training, we approximate policy actions from intermediate denoising steps via expected-target estimation. This allows the transport-field update to propagate into the network parameters without unstable backpropagation through time. Experimental results demonstrate that RLDT outperforms competitive baselines in reward quality and convergence speed. This performance holds across diverse continuous-control tasks, encompassing both dense and sparse rewards, as well as state- and vision-based long-horizon robot manipulation. The project webpage is \href{https://rpfey.github.io/rldt/}{https://rpfey.github.io/rldt/}.

cs.LG↗

arXiv2026

ActiveGrasp: Information-Guided Active Grasping with Calibrated Energy-based Model

Grasping in a densely cluttered environment is a challenging task for robots. Previous methods tried to solve this problem by actively gathering multiple views before grasp pose generation. However, they either overlooked the importance of the grasp distribution for information gain estimation or relied on the projection of the grasp distribution, which ignores the structure of grasp poses on the SE(3) manifold. To tackle these challenges, we propose a calibrated energy-based model for grasp pose generation and an active view selection method that estimates information gain from grasp distribution. Our energy-based model captures the multi-modality nature of grasp distribution on the SE(3) manifold. The energy level is calibrated to the success rate of grasps so that the predicted distribution aligns with the real distribution. The next best view is selected by estimating the information gain for grasp from the calibrated distribution conditioned on the reconstructed environment, which could efficiently drive the robot to explore affordable parts of the target object. Experiments on simulated environments and real robot setups demonstrate that our model could successfully grasp objects in a cluttered environment with limited view budgets compared to previous state-of-the-art models. Our simulated environment can serve as a reproducible platform for future research on active grasping. The source code of our paper will be made public when the paper is released to the public.

cs.RO↗

arXiv2025

Active Next-Best-View Optimization for Risk-Averse Path Planning

Safe navigation in uncertain environments requires planning methods that integrate risk aversion with active perception. In this work, we present a unified framework that refines a coarse reference path by constructing tail-sensitive risk maps from Average Value-at-Risk statistics on an online-updated 3D Gaussian-splat Radiance Field. These maps enable the generation of locally safe and feasible trajectories. In parallel, we formulate Next-Best-View (NBV) selection as an optimization problem on the SE(3) pose manifold, where Riemannian gradient descent maximizes an expected information gain objective to reduce uncertainty most critical for imminent motion. Our approach advances the state-of-the-art by coupling risk-averse path refinement with NBV planning, while introducing scalable gradient decompositions that support efficient online updates in complex environments. We demonstrate the effectiveness of the proposed framework through extensive computational studies.

cs.RO↗

arXiv2025

Multimodal LLM Guided Exploration and Active Mapping using Fisher Information

We present an active mapping system that plans for both long-horizon exploration goals and short-term actions using a 3D Gaussian Splatting (3DGS) representation. Existing methods either do not take advantage of recent developments in multimodal Large Language Models (LLM) or do not consider challenges in localization uncertainty, which is critical in embodied agents. We propose employing multimodal LLMs for long-horizon planning in conjunction with detailed motion planning using our information-based objective. By leveraging high-quality view synthesis from our 3DGS representation, our method employs a multimodal LLM as a zero-shot planner for long-horizon exploration goals from the semantic perspective. We also introduce an uncertainty-aware path proposal and selection algorithm that balances the dual objectives of maximizing the information gain for the environment while minimizing the cost of localization errors. Experiments conducted on the Gibson and Habitat-Matterport 3D datasets demonstrate state-of-the-art results of the proposed method.

cs.RO↗

arXiv2025

TensorTouch: Calibration of Tactile Sensors for High Resolution Stress Tensor and Deformation for Dexterous Manipulation

Advanced dexterous manipulation involving multiple simultaneous contacts across different surfaces, like pinching coins from ground or manipulating intertwined objects, remains challenging for robotic systems. Such tasks exceed the capabilities of vision and proprioception alone, requiring high-resolution tactile sensing with calibrated physical metrics. Raw optical tactile sensor images, while information-rich, lack interpretability and cross-sensor transferability, limiting their real-world utility. TensorTouch addresses this challenge by integrating finite element analysis with deep learning to extract comprehensive contact information from optical tactile sensors, including stress tensors, deformation fields, and force distributions at pixel-level resolution. The TensorTouch framework achieves sub-millimeter position accuracy and precise force estimation while supporting large sensor deformations crucial for manipulating soft objects. Experimental validation demonstrates 90% success in selectively grasping one of two strings based on detected motion, enabling new contact-rich manipulation capabilities previously inaccessible to robotic systems.

cs.RO↗

arXiv2025

Next Best Sense: Guiding Vision and Touch with FisherRF for 3D Gaussian Splatting

We propose a framework for active next best view and touch selection for robotic manipulators using 3D Gaussian Splatting (3DGS). 3DGS is emerging as a useful explicit 3D scene representation for robotics, as it has the ability to represent scenes in a both photorealistic and geometrically accurate manner. However, in real-world, online robotic scenes where the number of views is limited given efficiency requirements, random view selection for 3DGS becomes impractical as views are often overlapping and redundant. We address this issue by proposing an end-to-end online training and active view selection pipeline, which enhances the performance of 3DGS in few-view robotics settings. We first elevate the performance of few-shot 3DGS with a novel semantic depth alignment method using Segment Anything Model 2 (SAM2) that we supplement with Pearson depth and surface normal loss to improve color and depth reconstruction of real-world scenes. We then extend FisherRF, a next-best-view selection method for 3DGS, to select views and touch poses based on depth uncertainty. We perform online view selection on a real robot system during live 3DGS training. We motivate our improvements to few-shot GS scenes, and extend depth-based FisherRF to them, where we demonstrate both qualitative and quantitative improvements on challenging robot scenes. For more information, please see our project page at https://arm.stanford.edu/next-best-sense.

cs.RO↗

arXiv2025

Beyond Uncertainty: Risk-Aware Active View Acquisition for Safe Robot Navigation and 3D Scene Understanding with FisherRF

The active view acquisition problem has been extensively studied in the context of robot navigation using NeRF and 3D Gaussian Splatting. To enhance scene reconstruction efficiency and ensure robot safety, we propose the Risk-aware Environment Masking (RaEM) framework. RaEM leverages coherent risk measures to dynamically prioritize safety-critical regions of the unknown environment, guiding active view acquisition algorithms toward identifying the next-best-view (NBV). Integrated with FisherRF, which selects the NBV by maximizing expected information gain, our framework achieves a dual objective: improving robot safety and increasing efficiency in risk-aware 3D scene reconstruction and understanding. Extensive high-fidelity experiments validate the effectiveness of our approach, demonstrating its ability to establish a robust and safety-focused framework for active robot exploration and 3D scene understanding.

cs.RO↗

arXiv2024

FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information

This study addresses the challenging problem of active view selection and uncertainty quantification within the domain of Radiance Fields. Neural Radiance Fields (NeRF) have greatly advanced image rendering and reconstruction, but the cost of acquiring images poses the need to select the most informative viewpoints efficiently. Existing approaches depend on modifying the model architecture or hypothetical perturbation field to indirectly approximate the model uncertainty. However, selecting views from indirect approximation does not guarantee optimal information gain for the model. By leveraging Fisher Information, we directly quantify observed information on the parameters of Radiance Fields and select candidate views by maximizing the Expected Information Gain(EIG). Our method achieves state-of-the-art results on multiple tasks, including view selection, active mapping, and uncertainty quantification, demonstrating its potential to advance the field of Radiance Fields.

cs.CV↗

arXiv2023

Multi-Risk-RRT: An Efficient Motion Planning Algorithm for Robotic Autonomous Luggage Trolley Collection at Airports

Robots have become increasingly prevalent in dynamic and crowded environments such as airports and shopping malls. In these scenarios, the critical challenges for robot navigation are reliability and timely arrival at predetermined destinations. While existing risk-based motion planning algorithms effectively reduce collision risks with static and dynamic obstacles, there is still a need for significant performance improvements. Specifically, the dynamic environments demand more rapid responses and robust planning. To address this gap, we introduce a novel risk-based multi-directional sampling algorithm, Multi-directional Risk-based Rapidly-exploring Random Tree (Multi-Risk-RRT). Unlike traditional algorithms that solely rely on a rooted tree or double trees for state space exploration, our approach incorporates multiple sub-trees. Each sub-tree independently explores its surrounding environment. At the same time, the primary rooted tree collects the heuristic information from these sub-trees, facilitating rapid progress toward the goal state. Our evaluations, including simulation and real-world environmental studies, demonstrate that Multi-Risk-RRT outperforms existing unidirectional and bi-directional risk-based algorithms in planning efficiency and robustness.

cs.RO↗

arXiv2023

GRM: Gradient Rectification Module for Visual Place Retrieval

Visual place retrieval aims to search images in the database that depict similar places as the query image. However, global descriptors encoded by the network usually fall into a low dimensional principal space, which is harmful to the retrieval performance. We first analyze the cause of this phenomenon, pointing out that it is due to degraded distribution of the gradients of descriptors. Then, we propose Gradient Rectification Module(GRM) to alleviate this issue. GRM is appended after the final pooling layer and can rectify gradients to the complementary space of the principal space. With GRM, the network is encouraged to generate descriptors more uniformly in the whole space. At last, we conduct experiments on multiple datasets and generalize our method to classification task under prototype learning framework.

cs.CV↗

arXiv2022

SuperGF: Unifying Local and Global Features for Visual Localization

Advanced visual localization techniques encompass image retrieval challenges and 6 Degree-of-Freedom (DoF) camera pose estimation, such as hierarchical localization. Thus, they must extract global and local features from input images. Previous methods have achieved this through resource-intensive or accuracy-reducing means, such as combinatorial pipelines or multi-task distillation. In this study, we present a novel method called SuperGF, which effectively unifies local and global features for visual localization, leading to a higher trade-off between localization accuracy and computational efficiency. Specifically, SuperGF is a transformer-based aggregation model that operates directly on image-matching-specific local features and generates global features for retrieval. We conduct experimental evaluations of our method in terms of both accuracy and efficiency, demonstrating its advantages over other methods. We also provide implementations of SuperGF using various types of local features, including dense and sparse learning-based or hand-crafted descriptors.

cs.CV↗