Searcharxiv⌕ Search

arXiv subjects

German Devchich

Publications and source records attributed to German Devchich.

4 recordsLinked to original sources

CLIFT: Contrastive LiDAR Instance Features for 3D Pedestrian Tracking

A social robot has to keep track of the people around it over time to plan its motion, a task handled by 3D multi-object tracking. For the LiDAR modality, trackers usually sit on top of a detector and link its detections across frames with a separate motion model or re-identification network. We instead show how a 3D LiDAR detector itself can be turned into a tracker by adding an instance-level contrastive objective on its intermediate voxel features. Each embedding is read from the voxels inside a detected box, and boxes are matched across frames by cosine similarity and the Hungarian algorithm, without a motion model. The detector backbone is fine-tuned together with this objective, which learns identity-aware features while leaving detection accuracy essen- tially intact. Because the method uses only the voxel features that Li- DAR detectors already produce, it is backbone-agnostic. On the JRDB 3D tracking leaderboard our LiDAR-only tracker ranks first on HOTA (38.58) and IDF1 (37.99), 13.04 and 9.30 points above the next pub- lished method, and second on MOTA and OSPA. Code is available at https://hermak56.github.io/CLIFT/.

cs.CV↗

MuViSeg: Multi-View Segment Correspondences from Dense Geometry Priors

Object-level mapping and topological navigation reason about whole objects, yet the correspondences they rely on are computed over keypoints or pixels and only aggregated into objects afterwards. A recent line of work removes this detour by matching directly at the level of instance segments: a class-agnostic segmenter partitions each image, and per-segment descriptors are pooled from large 3D foundation models over the masks. This shifts the open question to how frozen foundation features should be processed once the unit of matching is a segment. We introduce MuViSeg, three learned matching heads: a LightGlue-style attention head on frozen MASt3R descriptors; a DPT-style multi-scale fusion module that exposes layered spatial detail from VGGT before pooling; and, as our main contribution, a joint multi-view head that attends over segments from several views at once, recovering transitive correspondences that pairwise matchers cannot express. In zero-shot evaluation on Replica and Virtual KITTI 2 across 0--180 degree viewpoint changes, our heads consistently improve over a parameter-free Sinkhorn matcher on the same backbone. Across 102 HM3D navigation episodes, direct segment matchers and sparse keypoint aggregation are statistically indistinguishable, while dense matches voted into masks lose 13.7--18.0 SPL.

cs.CV↗

EgoWalk: A Multimodal Dataset for Robot Navigation in the Wild

Data-driven navigation algorithms are critically dependent on large-scale, high-quality real-world data collection for successful training and robust performance in realistic and uncontrolled conditions. To enhance the growing family of navigation-related real-world datasets, we introduce EgoWalk - a dataset of 50 hours of human navigation in a diverse set of indoor/outdoor, varied seasons, and location environments. Along with the raw and Imitation Learning-ready data, we introduce several pipelines to automatically create subsidiary datasets for other navigation-related tasks, namely natural language goal annotations and traversability segmentation masks. Diversity studies, use cases, and benchmarks for the proposed dataset are provided to demonstrate its practical applicability. We openly release all data processing pipelines and the description of the hardware platform used for data collection to support future research and development in robot navigation systems.

cs.RO↗

PixelNav: Towards Model-based Vision-Only Navigation with Topological Graphs

This work proposes a novel hybrid approach for vision-only navigation of mobile robots, which combines advances of both deep learning approaches and classical model-based planning algorithms. Today, purely data-driven end-to-end models are dominant solutions to this problem. Despite advantages such as flexibility and adaptability, the requirement of a large amount of training data and limited interpretability are the main bottlenecks for their practical applications. To address these limitations, we propose a hierarchical system that utilizes recent advances in model predictive control, traversability estimation, visual place recognition, and pose estimation, employing topological graphs as a representation of the target environment. Using such a combination, we provide a scalable system with a higher level of interpretability compared to end-to-end approaches. Extensive real-world experiments show the efficiency of the proposed method.

cs.RO↗