Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning

Humans exhibit diverse and expressive whole-body movements. However, attaining human-like whole-body coordination in humanoid robots remains challenging, as conventional approaches that mimic whole-body motions often neglect the distinct roles of upper and lower body. This oversight leads to computationally intensive policy learning and frequently causes robot instability and falls during real-world execution. To address these issues, we propose Adversarial Locomotion and Motion Imitation (ALMI), a novel framework that enables adversarial policy learning between upper and lower body. Specifically, the lower body aims to provide robust locomotion capabilities to follow velocity commands while the upper body tracks various motions. Conversely, the upper-body policy ensures effective motion tracking when the robot executes velocity-based movements. Through iterative updates, these policies achieve coordinated whole-body control, which can be extended to loco-manipulation tasks with teleoperation systems. Extensive experiments demonstrate that our method achieves robust locomotion and precise motion tracking in both simulation and on the full-size Unitree H1 robot. Additionally, we release a large-scale whole-body motion control dataset featuring high-quality episodic trajectories from MuJoCo simulations deployable on real robots. The project page is https://almi-humanoid.github.io.

Intelligent LiDAR Navigation: Leveraging External Information and Semantic Maps with LLM as Copilot

Traditional robot navigation systems primarily utilize occupancy grid maps and laser-based sensing technologies, as demonstrated by the popular move_base package in ROS. Unlike robots, humans navigate not only through spatial awareness and physical distances but also by integrating external information, such as elevator maintenance updates from public notification boards and experiential knowledge, like the need for special access through certain doors. With the development of Large Language Models (LLMs), which posses text understanding and intelligence close to human performance, there is now an opportunity to infuse robot navigation systems with a level of understanding akin to human cognition. In this study, we propose using osmAG (Area Graph in OpensStreetMap textual format), an innovative semantic topometric hierarchical map representation, to bridge the gap between the capabilities of ROS move_base and the contextual understanding offered by LLMs. Our methodology employs LLMs as actual copilot in robot navigation, enabling the integration of a broader range of informational inputs while maintaining the robustness of traditional robotic navigation systems. Our code, demo, map, experiment results can be accessed at https://github.com/xiexiexiaoxiexie/Intelligent-LiDAR-Navigation-LLM-as-Copilot.

Collecting Larg-Scale Robotic Datasets on a High-Speed Mobile Platform

Mobile robotics datasets are essential for research on robotics, for example for research on Simultaneous Localization and Mapping (SLAM). Therefore the ShanghaiTech Mapping Robot was constructed, that features a multitude high-performance sensors and a 16-node cluster to collect all this data. That robot is based on a Clearpath Husky mobile base with a maximum speed of 1 meter per second. This is fine for indoor datasets, but to collect large-scale outdoor datasets a faster platform is needed. This system paper introduces our high-speed mobile platform for data collection. The mapping robot is secured on the rear-steered flatbed car with maximum field of view. Additionally two encoders collect odometry data from two of the car wheels and an external sensor plate houses a downlooking RGB and event camera. With this setup a dataset of more than 10km in the underground parking garage and the outside of our campus was collected and is published with this paper.

High-Quality, ROS Compatible Video Encoding and Decoding for High-Definition Datasets

Robotic datasets are important for scientific benchmarking and developing algorithms, for example for Simultaneous Localization and Mapping (SLAM). Modern robotic datasets feature video data of high resolution and high framerates. Storing and sharing those datasets becomes thus very costly, especially if more than one camera is used for the datasets. It is thus essential to store this video data in a compressed format. This paper investigates the use of modern video encoders for robotic datasets. We provide a software that can replay mp4 videos within ROS 1 and ROS 2 frameworks, supporting the synchronized playback in simulated time. Furthermore, the paper evaluates different encoders and their settings to find optimal configurations in terms of resulting size, quality and encoding time. Through this work we show that it is possible to store and share even highest quality video datasets within reasonable storage constraints.

Benchmarking SLAM Algorithms in the Cloud: The SLAM Hive System

Evaluating the performance of Simultaneous Localization and Mapping (SLAM) algorithms is essential for scientists and users of robotic systems alike. But there are a multitude different permutations of possible options of hardware setups and algorithm configurations, as well as different datasets and algorithms, such that it is infeasible to thoroughly compare SLAM systems against the full state of the art. To solve that we present the SLAM Hive Benchmarking Suite, which is able to analyze SLAM algorithms in thousands of mapping runs, through its utilization of container technology and deployment in the cloud. This paper presents the architecture and open source implementation of SLAM Hive and compares it to existing efforts on SLAM evaluation. We perform mapping runs of many of the most popular visual and LiDAR based SLAM algorithms against commonly used datasets and show how SLAM Hive and then be used to conveniently analyze the results against various aspects. Through this we envision that SLAM Hive can become an essential tool for proper comparisons and evaluations of SLAM algorithms and thus drive the scientific development in the research on SLAM. The open source software as well as a demo to show the live analysis of 100s of mapping runs can be found on our SLAM Hive website.

ShanghaiTech Mapping Robot is All You Need: Robot System for Collecting Universal Ground Vehicle Datasets

This paper presents the ShanghaiTech Mapping Robot, a state-of-the-art unmanned ground vehicle (UGV) designed for collecting comprehensive multi-sensor datasets to support research in robotics, computer vision, and autonomous driving. The robot is equipped with a wide array of sensors including RGB cameras, RGB-D cameras, event-based cameras, IR cameras, LiDARs, mmWave radars, IMUs, ultrasonic range finders, and a GNSS RTK receiver. The sensor suite is integrated onto a specially designed mechanical structure with a centralized power system and a synchronization mechanism to ensure spatial and temporal alignment of the sensor data. A 16-node on-board computing cluster handles sensor control, data collection, and storage. We describe the hardware and software architecture of the robot in detail and discuss the calibration procedures for the various sensors. The capabilities of the platform are demonstrated through an extensive dataset collected in diverse real-world environments. To facilitate research, we make the dataset publicly available along with the associated robot sensor calibration data. Performance evaluations on a set of standard perception and localization tasks showcase the potential of the dataset to support developments in Robot Autonomy.

Detection and Utilization of Reflections in LiDAR Scans Through Plane Optimization and Plane SLAM

In LiDAR sensing, glass, mirrors and other material often cause inconsistent data readings, because the laser beams may report the distance of the glass, the distance of the object behind the glass or the distance to a reflected object. This causes problems in robotics and 3D reconstruction, especially with respect to localization, mapping and thus navigation. With dual-return LiDARs and other methods, one can detect the glass plane and classify the points in a single scan. In this work we go one step further and construct a global, optimized map of reflective planes, in order to then classify all LiDAR readings at the end. As our experiments will show, this approach provides superior classification accuracy compared to the single scan approach. The code and data for this work are available as open source online.

Empowering Robotics with Large Language Models: osmAG Map Comprehension with LLMs

Recently, Large Language Models (LLMs) have demonstrated great potential in robotic applications by providing essential general knowledge for situations that can not be pre-programmed beforehand. Generally speaking, mobile robots need to understand maps to execute tasks such as localization or navigation. In this letter, we address the problem of enabling LLMs to comprehend Area Graph, a text-based map representation, in order to enhance their applicability in the field of mobile robotics. Area Graph is a hierarchical, topometric semantic map representation utilizing polygons to demark areas such as rooms, corridors or buildings. In contrast to commonly used map representations, such as occupancy grid maps or point clouds, osmAG (Area Graph in OpensStreetMap format) is stored in a XML textual format naturally readable by LLMs. Furthermore, conventional robotic algorithms such as localization and path planning are compatible with osmAG, facilitating this map representation comprehensible by LLMs, traditional robotic algorithms and humans. Our experiments show that with a proper map representation, LLMs possess the capability to understand maps and answer queries based on that understanding. Following simple fine-tuning of LLaMA2 models, it surpassed ChatGPT-3.5 in tasks involving topology and hierarchy understanding. Our dataset, dataset generation code, fine-tuned LoRA adapters can be accessed at https://github.com/xiefujing/LLM-osmAG-Comprehension.

3DRef: 3D Dataset and Benchmark for Reflection Detection in RGB and Lidar Data

Reflective surfaces present a persistent challenge for reliable 3D mapping and perception in robotics and autonomous systems. However, existing reflection datasets and benchmarks remain limited to sparse 2D data. This paper introduces the first large-scale 3D reflection detection dataset containing more than 50,000 aligned samples of multi-return Lidar, RGB images, and 2D/3D semantic labels across diverse indoor environments with various reflections. Textured 3D ground truth meshes enable automatic point cloud labeling to provide precise ground truth annotations. Detailed benchmarks evaluate three Lidar point cloud segmentation methods, as well as current state-of-the-art image segmentation networks for glass and mirror detection. The proposed dataset advances reflection detection by providing a comprehensive testbed with precise global alignment, multi-modal data, and diverse reflective objects and materials. It will drive future research towards reliable reflection detection. The dataset is publicly available at http://3dref.github.io

RealDex: Towards Human-like Grasping for Robotic Dexterous Hand

In this paper, we introduce RealDex, a pioneering dataset capturing authentic dexterous hand grasping motions infused with human behavioral patterns, enriched by multi-view and multimodal visual data. Utilizing a teleoperation system, we seamlessly synchronize human-robot hand poses in real time. This collection of human-like motions is crucial for training dexterous hands to mimic human movements more naturally and precisely. RealDex holds immense promise in advancing humanoid robot for automated perception, cognition, and manipulation in real-world scenarios. Moreover, we introduce a cutting-edge dexterous grasping motion generation framework, which aligns with human experience and enhances real-world applicability through effectively utilizing Multimodal Large Language Models. Extensive experiments have demonstrated the superior performance of our method on RealDex and other open datasets. The complete dataset and code will be made available upon the publication of this work.