30 accepted papers
Large Language Model (LLM)-based robotic assembly assistance has gained significant research attention. It requires the injection of domain-specific knowledge to guide the assembly process through natural language interaction with humans. Despite some progress, existing methods represent knowledge i…
Recently spatial-temporal intelligence of Visual-Language Models (VLMs) has attracted much attention due to its importance for Autonomous Driving, Embodied AI and General Artificial Intelligence. Existing spatial-temporal benchmarks mainly focus on egocentric perspective reasoning with images/video…
Existing concept customization methods have achieved remarkable outcomes in high-fidelity and multi-concept customization. However, they often neglect the influence on the original model's behavior and capabilities when learning new personalized concepts. To address this issue, we propose PureCC. Pu
We propose S3LAM, a novel RGB-D SLAM system that leverages 2D surfel splatting to achieve geometrically accurate scene representations for simultaneous tracking and mapping. Unlike existing 3DGS-based SLAM approaches that rely on 3D Gaussian ellipsoids, we utilize 2D Gaussian surfels as primitives f…
Structure-Based Drug Design (SBDD) has emerged as a popular approach in drug discovery, leveraging three-dimensional protein structures to generate drug ligands. However, existing generative models encounter several key challenges: (1) Incorporating boundary condition constraints, (2) Integrating hi
Vision-language-action (VLA) models have recently shown strong potential in enabling robots to follow language instructions and execute precise actions. However, most VLAs are built upon vision-language models pretrained solely on 2D data, which lack accurate spatial awareness and hinder their abili…
Parametric point clouds are sampled from CAD shapes and are becoming increasingly common in industrial manufacturing. Most CAD-specific deep learning methods focus on geometric features, while overlooking constraints inherent in CAD shapes. This limits their ability to discern CAD shapes with simila…
With the development of Embodied AI, robotic research has increasingly focused on complex tasks. Existing simulation platforms, however, are often limited to idealized environments, single-task scenarios and lack data interoperability. This restricts task decomposition and multi-task learning. Addit…
While recent advances in suction grasping have shown remarkable progress, significant challenges persist particularly in cluttered and complex parcel handling scenarios. Current approaches are limited by (1) the lack of comprehensive parcel-specific suction grasp datasets and (2) poor adaptability t
Diffusion models for garment-centric human generation from text or image prompts have garnered emerging attention for their great application potential. However, existing methods often face a dilemma: lightweight approaches, such as adapters, are prone to generate inconsistent textures; while finetu…
Embodied intelligence requires precise reconstruction and rendering to simulate large-scale real-world data. Although 3D Gaussian Splatting (3DGS) has recently demonstrated high-quality results with real-time performance, it still faces challenges in indoor scenes with large, textureless regions, re
As large language models (LLMs) become widely adopted, ensuring their alignment with human values is crucial to prevent jailbreaks where adversaries manipulate models to produce harmful content. While most defenses target single-turn attacks, real-world usage often involves multi-turn dialogues, exp
Transformers have achieved significant success in medical image segmentation, owing to their capability to capture long-range dependencies. Previous studies have employed either pure Transformer or hybrid CNN-Transformer architectures in the encoder module to enhance their ability to extract more co…
The trend of employing training-free methods for point cloud recognition is becoming increasingly popular due to its significant reduction in computational resources and time costs. However, existing approaches are limited as they typically extract either geometric or semantic features. To address t…
Safe and efficient mobility is vital for mobile robots navigating long-range indoor crowd environments, such as supermarkets, restaurants, and railway stations. Traditional path planning methods are challenged because of the high dynamics of pedestrians and constrained feasible regions. Existing lon…
In recent years, the rapid increase in scientific papers has overwhelmed traditional review mechanisms, resulting in varying quality of publications. Although existing methods have explored the capabilities of Large Language Models (LLMs) for automated scientific reviewing, their generated contents…
Predicting the plausible future paths of pedestrians is essential for human-involved applications (e.g., autonomous driving and service robotics). Existing pedestrian trajectory prediction methods mainly focus on the performance of multi-scene trained models in single-scene tests, neglecting the cro
To improve robot relocalization accuracy in both static and dynamic environments, we introduce a novel network, FusedNet, which incorporates a cross-attention to fuse global and local image features for end-to-end relocalization. This approach relies solely on a monocular camera sensor that is fixed
Recent works have shown that Large Language Models (LLMs) can facilitate the grounding of instructions for robotic task planning. Despite this progress, most existing works have primarily focused on utilizing raw images to aid LLMs in understanding environmental information. However, this approach n
Most existing robotic datasets capture static scene data and thus are limited in evaluating robots’ dynamic performance. To address this, we present a mobile robot oriented large-scale indoor dataset, denoted as THUD (Tsinghua University Dynamic) robotic dataset, for training and evaluating their dy…
Most industrial parts are designed from parametric shapes with the properties of diversity and uncertainty. We propose a 6DoF pose estimation network, ParametricNet++, based on pointwise regression and sparse keypoint recovery, which is extended from ParametricNet to include optimizations of keypoin…
Despite the success of 6D pose estimation in bin-picking scenarios, existing methods still struggle to produce accurate prediction results for symmetry objects in real-world scenarios. The primary bottlenecks include 1) the ambiguity in keypoints caused by object symmetries; and 2) the domain gap be…
Training with simulated data is a common approach in pose estimation research. However, a sim-to-real gap between clean simulated data and noisy real data will seriously weaken the generalization ability of the algorithm, especially for point clouds. To address this problem, this paper proposes a do…
Grasping an object when it is in an ungraspable pose is a challenging task, such as books or other large flat objects placed horizontally on a table. Inspired by human manipulation, we address this problem by pushing the object to the edge of the table and then grasping it from the hanging part. In…
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover, the model's judgment becomes noisier in real-world applicatio…
Convolution has been used for fast computation of reachability maps, but it has high computational costs when performing SE(3) convolution operations for general joint arrangements in industrial robots and 3D workspace. Its application is also limited to planar robots, 2D workspace, or robots with s…
Most industrial parts are parametric and their special properties are not fully explored yet. This paper proposes a new 6DoF pose estimation network for parametric shapes in stacked scenarios (ParametricNet). It treats a parametric shape, instead of a part object, as a category. The keypoints of ind…
Accurate object 6D pose estimation is a core task for robot bin-picking applications, especially when objects are randomly stacked with heavy occlusion. To address this problem, this paper proposes a simple but novel Point-wise Pose Regression Network (PPR-Net). For each point in the point cloud, th…
Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. Towards this we propose a novel convolutional architecture, termed SpiderCNN, to efficiently extract…