Jun Wu

Xuecheng Xu, Sha Lu, Jun Wu et al.

Global localization plays a critical role in many robot applications. LiDAR-based global localization draws the community's focus with its robustness against illumination and seasonal changes. To further improve the localization under large viewpoint differences, we propose RING++ which has roto-translation invariant representation for place recognition, and global convergence for both rotation and translation estimation. With the theoretical guarantee, RING++ is able to address the large viewpoint difference using a lightweight map with sparse scans. In addition, we derive sufficient conditions of feature extractors for the representation preserving the roto-translation invariance, making RING++ a framework applicable to generic multi-channel features. To the best of our knowledge, this is the first learning-free framework to address all subtasks of global localization in the sparse scan map. Validations on real-world datasets show that our approach demonstrates better performance than state-of-the-art learning-free methods, and competitive performance with learning-based methods. Finally, we integrate RING++ into a multi-robot/session SLAM system, performing its effectiveness in collaborative applications.

Yuxin Qi, Xi Lin, Jun Wu

Graph Neural Networks (GNNs) with differential privacy have been proposed to preserve graph privacy when nodes represent personal and sensitive information. However, the existing methods ignore that nodes with different importance may yield diverse privacy demands, which may lead to over-protect some nodes and decrease model utility. In this paper, we study the problem of importance-grained privacy, where nodes contain personal data that need to be kept private but are critical for training a GNN. We propose NAP-GNN, a node-importance-grained privacy-preserving GNN algorithm with privacy guarantees based on adaptive differential privacy to safeguard node information. First, we propose a Topology-based Node Importance Estimation (TNIE) method to infer unknown node importance with neighborhood and centrality awareness. Second, an adaptive private aggregation method is proposed to perturb neighborhood aggregation from node-importance-grain. Third, we propose to privately train a graph learning algorithm on perturbed aggregations in adaptive residual connection mode over multi-layers convolution for node-wise tasks. Theoretically analysis shows that NAP-GNN satisfies privacy guarantees. Empirical experiments over real-world graph datasets show that NAP-GNN achieves a better trade-off between privacy and accuracy.

Zhiwei Jin, Xiaohui Song, Nan Wang et al.

In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they significantly surpass the limitations in memory, power consumption, and computing capacity of edge devices such as mobile phones. This paper introduces AndesVL, a suite of mobile-side MLLMs with 0.6B to 4B parameters based on Qwen3's LLM and various visual encoders. We comprehensively outline the model architectures, training pipeline, and training data of AndesVL, which achieves first-tier performance across a wide range of open-source benchmarks, including fields such as text-rich image understanding, reasoning and math, multi-image comprehension, general VQA, hallucination mitigation, multilingual understanding, and GUI-related tasks when compared with state-of-the-art models of a similar scale. Furthermore, we introduce a 1+N LoRA architecture alongside a Quantization-Aware LoRA Fine-Tuning (QALFT) framework to facilitate efficient task adaptation and model compression during mobile-side deployment of AndesVL. Moreover, utilizing our cache eviction algorithm -- OKV -- along with customized speculative decoding and compression strategies, we achieve a 6.7x peak decoding speedup ratio, up to 30.9% memory reduction, and 1.8 bits-per-weight when deploying AndesVL-4B on MediaTek Dimensity 9500 chips. We release all models on https://huggingface.co/OPPOer.

Sander C. van den Berg, Rob B. N. Scharff, Zoltán Rusák et al.

We present OpenFish: an open source soft robotic fish which is optimized for speed and efficiency. The soft robotic fish uses a combination of an active and passive tail segment to accurately mimic the thunniform swimming mode. Through the implementation of a novel propulsion system that is capable of achieving higher oscillation frequencies with a more sinusoidal waveform, the open source soft robotic fish achieves a top speed of $0.85~\mathrm{m/s}$. Hereby, it outperforms the previously reported fastest soft robotic fish by $27\%$. Besides the propulsion system, the optimization of the fish morphology played a crucial role in achieving this speed. In this work, a detailed description of the design, construction and customization of the soft robotic fish is presented. Hereby, we hope this open source design will accelerate future research and developments in soft robotic fish.

Jiashi Zhang, Chengyang Zhang, Jun Wu et al.

The ubiquitous planes and structural consistency are the most apparent features of indoor multi-story Buildings compared with outdoor environments. In this paper, we propose a tightly coupled LiDAR-Inertial 3D SLAM framework with plane features for the multi-story building. The framework we proposed is mainly composed of three parts: tightly coupled LiDAR-Inertial odometry, extraction of representative planes of the structure, and factor graph optimization. By building a local map and inertial measurement unit (IMU) pre-integration, we get LiDAR scan-to-local-map matching and IMU measurements, respectively. Minimize the joint cost function to obtain the LiDAR-Inertial odometry information. Once a new keyframe is added to the graph, all the planes of this keyframe that can represent structural features are extracted to find the constraint between different poses and stories. A keyframe-based factor graph is conducted with the constraint of planes, and LiDAR-Inertial odometry for keyframe poses refinement. The experimental results show that our algorithm has outstanding performance in accuracy compared with the state-of-the-art algorithms.

Rob B. N. Scharff, Guoxin Fang, Yingjun Tian et al.

Real-time proprioception is a challenging problem for soft robots, which have almost infinite degrees-of-freedom in body deformation. When multiple actuators are used, it becomes more difficult as deformation can also occur on actuators caused by interaction between each other. To tackle this problem, we present a method in this paper to sense and reconstruct 3D deformation on pneumatic soft robots by first integrating multiple low-cost sensors inside the chambers of pneumatic actuators and then using machine learning to convert the captured signals into shape parameters of soft robots. An exterior motion capture system is employed to generate the datasets for both training and testing. With the help of good shape parameterization, the 3D shape of a soft robot can be accurately reconstructed from signals obtained from multiple sensors. We demonstrate the effectiveness of this approach on two designs of soft robots -- a robotic joint and a deformable membrane. After parameterizing the deformation of these soft robots into compact shape parameters, we can effectively train the neural networks to reconstruct the 3D deformation from the sensor signals. The sensing and shape prediction pipeline can run at 50Hz in real-time on a consumer-level device.

Tim Kuipers, Eugeni L. Doubrovski, Jun Wu et al.

3D printing techniques such as Fused Deposition Modeling (FDM) have enabled the fabrication of complex geometry quickly and cheaply. High stiffness parts are produced by filling the 2D polygons of consecutive layers with contour-parallel extrusion toolpaths. Uniform width toolpaths consisting of inward offsets from the outline polygons produce over- and underfill regions in the center of the shape, which are especially detrimental to the mechanical performance of thin parts. In order to fill shapes with arbitrary diameter densely the toolpaths require adaptive width. Existing approaches for generating toolpaths with adaptive width result in a large variation in widths, which for some hardware systems is difficult to realize accurately. In this paper we present a framework which supports multiple schemes to generate toolpaths with adaptive width, by employing a function to decide the number of beads and their widths. Furthermore, we propose a novel scheme which reduces extreme bead widths, while limiting the number of altered toolpaths. We statistically validate the effectiveness of our framework and this novel scheme on a data set of representative 3D models, and physically validate it by developing a technique, called back pressure compensation, for off-the-shelf FDM systems to effectively realize adaptive width.