27 accepted papers
Offline reinforcement learning (RL) faces a critical challenge of overestimating the value of out-of-distribution (OOD) actions. Existing methods mitigate this issue by penalizing unseen samples, yet they fail to accurately identify OOD actions and may suppress beneficial exploration beyond the beh…
Generalizable Neural Radiance Fields (GeNeRF) enable high-quality scene reconstruction from a limited number of views and can generalize to unseen scenes. However, in real-world environments, transient distractors disrupt structural consistency across views, leading to deviated supervision signals a
Agentic systems have recently become the dominant paradigm for formal theorem proving, achieving strong performance by coordinating multiple models and tools. However, existing approaches often rely on task-specific pipelines and trained formal provers, limiting their flexibility and reproducibility…
Value function factorization is widely used in cooperative multi-agent reinforcement learning (MARL). Existing approaches often impose monotonicity constraints between the joint action value and individual action values to enable decentralized execution. However, such constraints limit the expressiv…
3D Gaussian Splatting has demonstrated remarkable potential in novel view synthesis. In contrast to small-scale scenes, large-scale scenes inevitably contain sparsely observed regions with excessively sparse initial points. In this case, supervising Gaussians initialized from low-frequency sparse po…
Commonly used asymptotically convergent sampling algorithms (SBP) often utilize the Informed Set (IS) to enhance sampling efficiency. However, IS typically requires obtaining a low-cost solution first, which is challenging when narrow passages are present in the environment. To address the narrow pa
Existing context-based offline meta-reinforcement learning (COMRL) methods primarily focus on task representation learning and given-context adaptation performance. They often assume that the adaptation context is collected using task-specific behavior policies or through multiple rounds of collecti…
Constrained hybrid-action reinforcement learning (RL) promises to learn a safe policy within a parameterized action space, which is particularly valuable for safety-critical applications involving discrete-continuous hybrid action spaces. However, existing hybrid-action RL algorithms primarily focus…
Using Quadrics as the object representation has the benefits of both generality and closed-form projection derivation between image and world spaces. Although numerous constraints have been proposed for dual quadric reconstruction, we found that many of them are imprecise and provide minimal improve
Collecting demonstrations enriched with fine-grained tactile information is critical for dexterous manipulation, particularly in contact-rich tasks that require precise force control and physical interaction. While prior works primarily focus on teleoperation or video-based retargeting, they often s…
Visual Place Recognition (VPR) enables robust localization through image retrieval based on learned descriptors. However, drastic appearance variations of images at the same place caused by viewpoint changes can lead to inconsistent supervision signals, thereby degrading descriptor learning. Exi…
Offline meta reinforcement learning (OMRL) has emerged as a promising approach for interaction avoidance and strong generalization performance by leveraging pre-collected data and meta-learning techniques. Previous context-based approaches predominantly rely on the intuition that alternating optimi…
Building accurate and reliable maps is a critical requirement for autonomous robots. In this paper, we propose UN3-Mapping, an implicit neural mapping method that enables high-quality 3D reconstruction with integrated uncertainty estimation. Our approach employs a hybrid representation: an implicit
A primary challenge for visual-based Reinforcement Learning (RL) is to generalize effectively across unseen environments. Although previous studies have explored different auxiliary tasks to enhance generalization, few adopt image reconstruction due to concerns about exacerbating overfitting to task…
Simultaneous localization and mapping (SLAM) is essential for autonomous driving. Most LiDAR-inertial SLAM algorithms assume a static environment, leading to unreliable localization in dynamic environments. Moreover, the accurate tracking of moving objects is of great significance for the control an
Uncertainty in LiDAR measurements, stemming from factors such as range sensing, is crucial for LIO (LiDAR-Inertial Odometry) systems as it affects the accurate weighting in the loss function. While recent LIO systems address uncertainty related to range sensing, the impact of incident angle on uncer
Local geometric information, i.e., normal and distribution of points, is crucial for LiDAR-based simultaneous localization and mapping (SLAM) because it provides constraints for data association, which further determines the direction of optimization and ultimately affects the accuracy of localizati
Visual Place Recognition (VPR) aims to retrieve frames from a geotagged database that are located at the same place as the query frame. To improve the robustness of VPR in perceptually aliasing scenarios, sequence-based VPR methods are proposed. These methods are either based on matching between fra
Accurate and dense mapping in large-scale environments is essential for various robot applications. Recently, implicit neural signed distance fields (SDFs) have shown promising advances in this task. However, most existing approaches employ projective distances from range data as SDF supervision, in
Safety is one of the main challenges in applying reinforcement learning to tasks in realistic environments. To ensure safety during and after the training process, existing methods tend to adopt overly conservative policies to avoid unsafe situations. However, an overly conservative policy severely
As a marriage between offline RL and meta-RL, the advent of offline meta-reinforcement learning (OMRL) has shown great promise in enabling RL agents to multi-task and quickly adapt while acquiring knowledge safely. Among which, context-based OMRL (COMRL) as a popular paradigm, aims to learn a univer…
Designing and deriving effective model-based reinforcement learning (MBRL) algorithms with a performance improvement guarantee is challenging, mainly attributed to the high coupling between model learning and policy optimization. Many prior methods that rely on return discrepancy to guide model lear…
We propose LIO-Vehicle, a new tightly-coupled vehicle dynamics extension of LiDAR inertial odometry (LIO) method that provides highly accurate, robust, and real-time vehicle trajectory estimation. Since most existing LiDAR-based localization methods are not specifically proposed for vehicles, they d
The scale ambiguity problem is inherently unsolvable to monocular SLAM without the metric baseline between moving cameras. In this paper, we present a novel scale estimation approach based on an object-level SLAM system. To obtain the absolute scale of the reconstructed map, we formulate an optimiza…
Real-time semantic segmentation is a challenging task as both accuracy and inference speed need to be considered simultaneously. In real-world applications, it is usually achieved by deploying a deep neural network in modern GPU device. However, most of the work focused on real-time semantic segment…
Herein, we present a novel approach for monocular dual quadric initialization that combines three-dimensional (3D) map points with two-dimensional (2D) object detection for forward-translating camera movements. The traditional approach using 2D detection bounding boxes in multiple views fails in str
For the domain of self-driving and automatic parking, perception is a basic and critical technique, moreover, the detection of lane markings and parking slots is an important part of visual perception. Compared with front sight images, panoramic images(PI) can capture more comprehensive pavement inf…