1 December 2021 in Case Studies in Thermal Engineering
1 August 2024 in IEEE Transactions on Automation Science and Engineering
The creation of a metric-semantic map, which encodes human-prior knowledge, represents a high-level abstraction of environments. However, constructing such a map poses challenges related to the fusion of multi-modal sensor data, the attainment of real-time mapping performance, and the preservation of structural and semantic information consistency. In this paper, we introduce an online metric-semantic mapping system that utilizes LiDAR-Visual-Inertial sensing to generate a global metric-semantic mesh map of large-scale outdoor environments. Leveraging GPU acceleration, our mapping process achieves exceptional speed, with frame processing taking less than $7ms$ , regardless of scenario scale. Furthermore, we seamlessly integrate the resultant map into a real-world navigation system, enabling metric-semantic-based terrain assessment and autonomous point-to-point navigation within a campus environment. Through extensive experiments conducted on both publicly available and self-collected datasets comprising $24$ sequences, we demonstrate the effectiveness of our mapping and navigation methodologies. Note to Practitioners —This paper tackles the challenge of autonomous navigation for mobile robots in complex, unstructured environments with rich semantic elements. Traditional navigation relies on geometric analysis and manual annotations, struggling to differentiate similar structures like roads and sidewalks. We propose an online mapping system that creates a global metric-semantic mesh map for large-scale outdoor environments, utilizing GPU acceleration for speed and overcoming the limitations of existing real-time semantic mapping methods, which are generally confined to indoor settings. Our map integrates into a real-world navigation system, proven effective in localization and terrain assessment through experiments with both public and proprietary datasets. Future work will focus on integrating kernel-based methods to improve the map’s semantic accuracy.
19 September 2022 in IEEE Robotics and Automation Letters
Safely interacting with other traffic participants is one of the core requirements for autonomous driving, especially in intersections and occlusions. Most existing approaches are designed for particular scenarios and require significant human labor in parameter tuning to be applied to different situations. To solve this problem, we first propose a learning-based Interaction Point Model (IPM), which describes the interaction between agents with the protection time and interaction priority in a unified manner. We further integrate the proposed IPM into a novel planning framework, demonstrating its effectiveness and robustness through comprehensive simulations in highly dynamic environments.
14 November 2025 in IEEE Transactions on Vehicular Technology
Integrating General Models (GMs) such as Large Language Models (LLMs), with Specialized Models (SMs) in autonomous driving tasks presents a promising approach to mitigating challenges in data diversity and model capacity of existing specialized driving models. However, this integration leads to problems of asynchronous systems, which arise from the distinct characteristics inherent in GMs and SMs. To tackle this challenge, we propose NetRoller, an adapter that incorporates a set of novel mechanisms to facilitate the seamless integration of GMs and specialized driving models. Specifically, our mechanisms for interfacing the asynchronous GMs and SMs are organized into three key stages. NetRoller first harvests semantically rich and computationally efficient representations from the reasoning processes of LLMs using an early stopping mechanism, which preserves critical insights on driving context while maintaining low overhead. It then applies learnable query embeddings, nonsensical embeddings, and positional layer embeddings to facilitate robust and efficient cross-modality translation. At last, it employs computationally efficient Query Shift and Feature Shift mechanisms to enhance the performance of SMs through few-epoch fine-tuning. Based on the mechanisms formalized in these three stages, NetRoller enables specialized driving models to operate at their native frequencies while maintaining situational awareness of the GM. Experiments conducted on the nuScenes dataset demonstrate that integrating GM through NetRoller significantly improves human similarity and safety in planning tasks, and it also achieves noticeable precision improvements in detection and mapping tasks for end-to-end autonomous driving. The code and models are available at https://github.com/Rex-sys-hk/NetRoller.
25 July 2025 in Machine Intelligence Research
Embodied intelligence applications, such as autonomous robotics and smart transportation systems, require efficient coordination of multiple agents in dynamic environments. A critical challenge in this domain is the multi-agent pathfinding (MAPF) problem, which ensures that agents can navigate conflict-free while optimizing their paths. Conflict-based search (CBS) is a well-established two-level solver for the MAPF problem. However, as the scale of the problem expands, the computation time becomes a significant challenge for the implementation of CBS. Previous optimizations have mainly focused on reducing the number of nodes explored by the high-level or low-level solver. This paper takes a different perspective by proposing a parallel version of CBS, namely GPU-accelerated conflict-based search (GACBS), which significantly exploits the parallel computing capabilities of GPU. GACBS employs a task coordination framework to enable collaboration between the high-level and low-level solvers with lightweight synchronous operations. Moreover, GACBS leverages a parallel low-level solver, called GATSA, to efficiently find the shortest path for a single agent under constraints. Experimental results show that the proposed GACBS significantly outperforms CPU-based CBS, with the maximum speedup ratio reaching over 46.