With the rapid development of AI and deep learning, computational demands are increasing significantly. While GPUs excel in parallel computing, they fall short in terms of energy efficiency, specialization, and processing latency. In contrast, Neural Processing Units (NPUs), such as the Ascend NPUs, designed specifically for deep learning tasks, demonstrate superior performance. However, the architecture specialization makes operator development more challenging, leading to a reliance on manual tuning and optimization, which incurs significant time cost and developing effort. To address this issue, we propose NPUMeter, an automatic operator optimization framework for Ascend NPUs built upon accurate and comprehensive analytical performance models. NPUMeter comprises two components: (1) an analytical performance model that accurately estimates operator latency on NPU given different configurations of optimization parameters; (2) an efficient design space exploration (DSE) algorithm that automatically searches for the optimal parameter configuration in a large design space within minutes. Experimental results demonstrate that NPUMeter achieves high estimation accuracy, with an average error below 5%. It effectively generates near-optimal configurations for various operators, achieving up to a 1.46× performance speedup compared to the configuration generated by the Ascend C compiler while reducing the DSE time from hours to minutes.

3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 frames per second (FPS) on resource-constrained mobile devices, achieving only 2 to 9 FPS. Existing accelerators focus on compute efficiency but overlook memory efficiency, leading to redundant DRAM traffic. We introduce STREAMINGGS, a fully streaming 3DGS algorithm-architecture co-design that achieves fine-grained pipelining and reduces DRAM traffic by transforming from a tile-centric rendering to a memory-centric rendering. Results show that our design achieves up to 45.7 × speedup and 62.9 × energy savings over mobile Ampere GPUs.

In complex missions such as search and rescue, robots must make intelligent decisions in unknown environments, relying on their ability to perceive and understand their surroundings. High-quality and real-time reconstruction enhances situational awareness and is crucial for intelligent robotics. Traditional methods often struggle with poor scene representation or are too slow for real-time use. Inspired by the efficacy of 3D Gaussian Splatting (3DGS), we propose a hierarchical planning framework for fast and high-fidelity active reconstruction. Our method evaluates completion and quality gain to adaptively guide reconstruction, integrating global and local planning for efficiency. Experiments in simulated and realworld environments show our approach outperforms existing real-time methods.

Automatic Emergency Braking (AEB) systems are a crucial component in ensuring the safety of passengers in autonomous vehicles. Conventional AEB systems primarily rely on closed-set perception modules to recognize traffic conditions and assess collision risks. To enhance the adaptability of AEB systems in open scenarios, we propose Dual-AEB, a system combines an advanced multimodal large language model (MLLM) for comprehensive scene understanding and a conventional rule-based rapid AEB to ensure quick response times. To the best of our knowledge, Dual-Aebis the first method to incorporate MLLMs within AEB systems. Through extensive experimentation, we have validated the effectiveness of our method. Codes will be publicly available at https://github.com/ChipsICU/Dual-AEB.

Trajectory optimization in multi-vehicle scenarios faces challenges due to its non-linear, non-convex properties and sensitivity to initial values, making interactions between vehicles difficult to control. In this paper, inspired by topological planning, we propose a differentiable local homotopy invariant metric to model the interactions. By incorporating this topological metric as a constraint into multi-vehicle trajectory optimization, our framework is capable of generating multiple interactive trajectories from the same initial values, achieving controllable interactions as well as supporting user-designed interaction patterns. Extensive experiments demonstrate its superior optimality and efficiency over existing methods. We will release open-source code to advance relative research1.

One of the unresolved challenges for autonomous vehicles is occlusion-aware decision-making under the high uncertainty of various occlusions. Recent occlusion-aware decision-making methods encounter issues such as overly conservative behavior, high computational complexity, or scenario scalability challenges. Benefiting from automatically generating data by exploration randomization, we uncover that reinforcement learning (RL) may show promise in occlusion-aware decision-making. However, previous occlusion-aware RL faces challenges in expanding to various dynamic and static occlusion scenarios, low learning efficiency, and lack of predictive ability. To address these issues, we introduce Pad-AI, a self-reinforcing framework to learn occlusion-aware decision-making through active perception. Pad-AI utilizes vectorized representation to represent occluded environments efficiently and learns over the semantic motion primitives to focus on high-level active perception exploration. Furthermore, Pad-AI integrates prediction and RL within a unified framework to provide risk-aware learning and reliable policy optimization. Our framework was tested in challenging scenarios under both dynamic and static occlusions and demonstrated efficient perception-aware exploration performance to other strong baselines in closed-loop evaluations.

In logistics systems with multiagent collaboration, one of the prevailing focus lies on modeling as the dynamic multiperiod vehicle routing problem (DMPVRP). This work introduces modifications to DMPVRP to align with the requirements of real factory operations, particularly with dynamic supply demands. A self-established multiagent dynamic scheduling framework has been proposed to adapt to dynamic environmental changes and make timely adjustments, which consists of two modules: dynamic path planning and machine assignment. The first module utilizes a self-designed multioperator two-stage evolutionary algorithm to dynamically update the routes for vehicles. The second module maintains the workload balance among vehicles in real time. Experimental results demonstrate that the proposed algorithm achieves optimal outcomes compared to three state-of-the-art algorithms, surpassing others by 20% in machine output and exhibiting 5% lower transportation costs. In addition, a case study from a steel cord manufacturing factory is conducted, demonstrating its capability to promptly enhance efficiency.

Online dense mapping of urban scenes is of paramount importance for scene understanding of autonomous navigation. Traditional online dense mapping methods fuse sensor measurements (vision, lidar, etc.) across time and space via explicit geometric correspondence. Recently, NeRF-based methods have proved the superiority of neural implicit representations by high-fidelity reconstruction of large-scale city scenes. However, it remains an open problem how to integrate powerful neural implicit representations into online dense mapping. Existing methods are restricted to constrained indoor environments and are too computationally expensive to meet online requirements. To this end, we propose Swift-Mapping, an online neural implicit dense mapping framework in urban scenes. We introduce a novel neural implicit octomap (NIO) structure that provides efficient neural representation for large and dynamic urban scenes while retaining online update capability. Based on that, we propose an online neural dense mapping framework that effectively manages and updates neural octree voxel features. Our approach achieves SOTA reconstruction accuracy while being more than 10x faster in reconstruction speed, demonstrating the superior performance of our method in both accuracy and efficiency.

Point clouds have shown significant potential in various domains, including Simultaneous Localization and Mapping (SLAM). However, existing approaches either rely on dense point clouds to achieve high localization accuracy or use generalized descriptors to reduce map size. Unfortunately, these two aspects seem to conflict with each other. To address this limitation, we propose an unified architecture, DeepPointMap, achieving excellent preference on both aspects. We utilize neural network to extract highly representative and sparse neural descriptors from point clouds, enabling memory-efficient map representation and accurate multi-scale localization tasks (e.g., odometry and loop-closure). Moreover, we showcase the versatility of our framework by extending it to more challenging multi-agent collaborative SLAM. The promising results obtained in these scenarios further emphasize the effectiveness and potential of our approach.

Recently, the use of large language models (LLMs) for software code generation, e.g., C/C++ and Python, has proven a great success. However, LLMs still suffer from low syntactic and functional correctness when it comes to the generation of register-transfer level (RTL) code, such as Verilog. To address this issue, in this paper, we develop AutoVCoder, a systematic open-source framework that significantly improves the LLMs' correctness of generating Verilog code and enhances the quality of its output at the same time. Our framework integrates three novel techniques, including a high-quality hardware dataset generation approach, a two-round LLM fine-tuning method and a domain-specific retrieval-augmented generation (RAG) mechanism. Experimental results demonstrate that AutoVCoder outperforms both industrial and academic LLMs in Verilog code generation. Code and models are available at https://github.com/sjtu-zhao-lab/AutoVCoder.

In the era of big data and large models, automatic annotating functions for multi-modal data are of great significance for real-world AI-driven applications, such as autonomous driving and embodied AI. Unlike traditional closed-set annotation, open-vocabulary annotation is essential to achieve human-level cognition capability. However, there are few open-vocabulary auto-labeling systems for multi-modal 3D data. In this paper, we introduce OpenAnnotate3D, an open-source open-vocabulary auto-labeling system that can automatically generate 2D masks, 3D masks, and 3D bounding box annotations for vision and point cloud data. Our system integrates the chain-of-thought capabilities of Large Language Models (LLMs) and the cross-modality capabilities of vision-language models (VLMs). To the best of our knowledge, OpenAnnotate3D is one of the pioneering works for open-vocabulary multi-modal 3D auto-labeling. We conduct comprehensive evaluations on both public and in-house real-world datasets, which demonstrate that the system significantly improves annotation efficiency compared to manual annotation while providing accurate open-vocabulary auto-annotating results.

Simultaneous Localization and Mapping (SLAM) plays a pivotal role in autonomous driving and robotics. Existing methods often rely on hand-craft feature extraction and cross-modal fusion techniques, resulting in limited feature representation capability and reduced robustness. To address this challenge, we introduce DeepPointMap2, a novel learning-based LiDAR-Visual SLAM architecture that leverages neural descriptors to tackle multiple SLAM sub-tasks in a unified manner. Our approach employs neural networks to extract multi-modal tokens, which are then adaptively fused by the Visual-Point Fusion Module to generate sparse 3D neural descriptors, ensuring precise and robust performance. As a pioneering work, our method achieves state-of-the-art localization performance among various Visual-, LiDAR-, and Visual-LiDAR-based methods in widely-used benchmarks, as shown in the experiment results. Furthermore, the approach proves to be robust in scenarios involving camera failure and LiDAR obstruction.

As DNNs are developing rapidly, the computational and memory burden imposed on hardware systems grows exponentially. This becomes even more severe for large language models (LLMs) and multimodal models. As a promising solution that achieves high scalability and low manufacturing cost, multiaccelerator systems widely exist in data centers, cloud platforms, and mobile SoCs. Thus, a challenging problem arises: selecting a proper combination of accelerators from available designs and searching for efficient DNN mapping strategies, to fully exploit computation resources and communication bandwidth in the system. To this end, we propose MARS, a novel mapping framework that performs computation-aware accelerator selection and applies communication-aware sharding strategies to maximize parallelism. We also provide optimizations to overlap the computation and communication latency. Considering the high complexity of the design space, we propose two effective mapping algorithms to explore it. Experiments show that MARS achieves 34.3% latency reduction for DNN workloads compared to the baseline and 63.0% latency reduction on heterogeneous models compared to the corresponding state-of-the-art method.

Along with the fast evolution of deep neural networks, the hardware system is also developing rapidly. As a promising solution achieving high scalability and low manufacturing cost, multi-accelerator systems widely exist in data centers, cloud platforms, and SoCs. Thus, a challenging problem arises in multi-accelerator systems: selecting a proper combination of accelerators from available designs and searching for efficient DNN mapping strategies. To this end, we propose MARS, a novel mapping framework that can perform computation-aware accelerator selection, and apply communication-aware sharding strategies to maximize parallelism. Experimental results show that MARS can achieve 32.2% latency reduction on average for typical DNN workloads compared to the baseline, and 59.4% latency reduction on heterogeneous models compared to the corresponding state-of-the-art method.

There is extensive literature on perceiving road structures by fusing various sensor inputs such as lidar point clouds and camera images using deep neural nets. Leveraging the latest advance of neural architects (such as transformers) and bird-eye-view (BEV) representation, the road cognition accuracy keeps improving. However, how to cognize the “road” for automated vehicles where there is no well-defined “roads” remains an open problem. For example, how to find paths inside intersections without HD maps is hard since there is neither an explicit definition for “roads” nor explicit features such as lane markings. The idea of this paper comes from a proverb: it becomes a way when people walk on it. Although there are no “roads” from sensor readings, there are “roads” from tracks of other vehicles. In this paper, we propose FlowMap, a path generation framework for automated vehicles based on traffic flows. FlowMap is built by extending our previous work RoadMap [1], a light-weight semantic map, with an additional traffic flow layer. A path generation algorithm on traffic flow fields (TFFs) is proposed to generate human-like paths. The proposed framework is validated using real-world driving data and is amenable to generating paths for super complicated intersections without using HD maps.

In this article, we present an efficient planning system for automated vehicles in highly interactive environments (EPSILON). EPSILON is an efficient interaction-aware planning system for automated driving, and is extensively validated in both simulation and real-world dense city traffic. It follows a hierarchical structure with an interactive behavior planning layer and an optimization-based motion planning layer. The behavior planning is formulated from a partially observable Markov decision process (POMDP), but is much more efficient than naively applying a POMDP to the decision-making problem. The key to efficiency is guided branching in both the action space and observation space, which decomposes the original problem into a limited number of closed-loop policy evaluations. Moreover, we introduce a new driver model with a safety mechanism to overcome the risk induced by the potential imperfectness of prior knowledge. For motion planning, we employ a spatio-temporal semantic corridor (SSC) to model the constraints posed by complex driving environments in a unified way. Based on the SSC, a safe and smooth trajectory is optimized, complying with the decision provided by the behavior planner. We validate our planning system in both simulations and real-world dense traffic, and the experimental results show that our EPSILON achieves human-like driving behaviors in highly interactive traffic flow smoothly and safely without being overconservative compared to the existing planning methods.

Fast and accurate depth estimation, or stereo matching, is essential in embedded stereo vision systems, requiring substantial design effort to achieve an appropriate balance among accuracy, speed and hardware cost. To reduce the design effort and achieve the right balance, we propose FP-Stereo for building high-performance stereo matching pipelines on FPGAs automatically. FP-Stereo consists of an open-source hardware-efficient library, allowing designers to obtain the desired implementation instantly. Diverse methods are supported in our library for each stage of the stereo matching pipeline and a series of techniques are developed to exploit the parallelism and reduce the resource overhead. To improve the usability, FP-Stereo can generate synthesizable C code of the FPGA accelerator with our optimized HLS templates automatically. To guide users for the right design choice meeting specific application requirements, detailed comparisons are performed on various configurations of our library to investigate the accuracy/speed/cost trade-off. Experimental results also show that FP-Stereo outperforms the state-of-the-art FPGA design from all aspects, including 6.08% lower error, 2x faster speed, 30% less resource usage and 40% less energy consumption. Compared to GPU designs, FP-Stereo achieves the same accuracy at a competitive speed while consuming much less energy.

Decision-making in dense traffic scenarios is challenging for automated vehicles (AVs) due to potentially stochastic behaviors of other traffic participants and perception uncertainties (e.g., tracking noise and prediction errors, etc.). Although the partially observable Markov decision process (POMDP) provides a systematic way to incorporate these uncertainties, it quickly becomes computationally intractable when scaled to the real-world large-size problem. In this paper, we present an efficient uncertainty-aware decision-making (EUDM) framework, which generates long-term lateral and longitudinal behaviors in complex driving environments in real-time. The computation complexity is controlled to an appropriate level by two novel techniques, namely, the domain-specific closed-loop policy tree (DCP-Tree) structure and conditional focused branching (CFB) mechanism. The key idea is utilizing domain-specific expert knowledge to guide the branching in both action and intention space. The proposed framework is validated using both onboard sensing data captured by a real vehicle and an interactive multi-agent simulation platform. We also release the code of our framework to accommodate benchmarking.

Anticipating possible behaviors of traffic participants is an essential capability of autonomous vehicles. Many behavior detection and maneuver recognition methods only have a very limited prediction horizon that leaves inadequate time and space for planning. To avoid unsatisfactory reactive decisions, it is essential to count long-term future rewards in planning, which requires extending the prediction horizon. In this paper, we uncover that clues to vehicle behaviors over an extended horizon can be found in vehicle interaction, which makes it possible to anticipate the likelihood of a certain behavior, even in the absence of any clear maneuver pattern. We adopt a recurrent neural network (RNN) for observation encoding, and based on that, we propose a novel vehicle behavior interaction network (VBIN) to capture the vehicle interaction from the hidden states and connection feature of each interaction pair. The output of our method is a probabilistic likelihood of multiple behavior classes, which matches the multimodal and uncertain nature of the distant future. A systematic comparison of our method against two state-of-the-art methods and another two baseline methods on a publicly available real highway dataset is provided, showing that our method has superior accuracy and advanced capability for interaction modeling.

In this paper, we present an online two-level vehicle trajectory prediction framework for urban autonomous driving where there are complex contextual factors, such as lane geometries, road constructions, traffic regulations and moving agents. Our method combines high-level policy anticipation with low-level context reasoning. We leverage a long short-term memory (LSTM) network to anticipate the vehicle's driving policy (e.g., forward, yield, turn left, turn right, etc.) using its sequential history observations. The policy is then used to guide a low-level optimization-based context reasoning process. We show that it is essential to incorporate the prior policy anticipation due to the multimodal nature of the future trajectory. Moreover, contrary to existing regression-based trajectory prediction methods, our optimization-based reasoning process can cope with complex contextual factors. The final output of the two-level reasoning process is a continuous trajectory that automatically adapts to different traffic configurations and accurately predicts future vehicle motions. The performance of the proposed framework is analyzed and validated in an emerging autonomous driving simulation platform (CARLA).

Trajectory replanning for quadrotors is essential to enable fully autonomous flight in unknown environments. Hierarchical motion planning frameworks, which combine path planning with path parameterization, are popular due to their time efficiency. However, the path planning cannot properly deal with nonstatic initial states of the quadrotor, which may result in nonsmooth or even dynamically infeasible trajectories. In this article, we present an efficient kinodynamic replanning framework by exploiting the advantageous properties of the B-spline, which facilitates dealing with the nonstatic state and guarantees safety and dynamical feasibility. Our framework starts with an efficient B-spline-based kinodynamic (EBK) search algorithm, which finds a feasible trajectory with minimum control effort and time. To compensate for the discretization induced by the EBK search, an elastic optimization approach is proposed to refine the control point placement to the optimal location. Systematic comparisons against the state-of-the-art are conducted to validate the performance. Comprehensive onboard experiments using two different vision-based quadrotors are carried out showing the general applicability of the framework.

Recently, physical layer (PHY) caching has been proposed to exploit the dynamic side information induced by caches at base stations (BSs) to support coordinated multi-point (CoMP) and achieve high degrees of freedom (DoF) gains. Due to the limited cache storage capacity, the performance of PHY caching depends heavily on the cache content placement algorithm. In the existing algorithms, the cache content placement is adaptive to the long-term popularity distribution in an offline manner. We propose an online PHY caching framework, which adapts the cache content placement to microscopic spatial and temporary popularity variations to fully exploit the benefits of PHY caching. Specifically, the joint optimization of online cache content placement and content delivery is formulated as a mixed-timescale drift minimization problem to increase the CoMP opportunity and reduce the cache content placement cost. We propose a low-complexity algorithm to obtain a throughput-optimal solution. Moreover, we provide a closed-form characterization of the maximum sum DoF in the stability region and study the impact of key system parameters on the stability region. The simulations results show that the proposed online PHY caching framework achieves large gain over existing solutions.

We focus on a replanning scenario for quadrotors where considering time efficiency, non-static initial state and dynamical feasibility is of great significance. We propose a real-time B-spline based kinodynamic (RBK) search algorithm, which transforms a position-only shortest path search (such as A * and Dijkstra) into an efficient kinodynamic search, by exploring the properties of B-spline parameterization. The RBK search is greedy and produces a dynamically feasible time-parameterized trajectory efficiently, which facilitates non-static initial state of the quadrotor. To cope with the limitation of the greedy search and the discretization induced by a grid structure, we adopt an elastic optimization (EO) approach as a post-optimization process, to refine the control point placement provided by the RBK search. The EO approach finds the optimal control point placement inside an expanded elastic tube which represents the free space, by solving a Quadratically Constrained Quadratic Programming (QCQP) problem. We design a receding horizon replanner based on the local control property of B-spline. A systematic comparison of our method against two state-of-the-art methods is provided. We integrate our replanning system with a monocular vision-based quadrotor and validate our performance onboard.

In this paper, we propose a novel mapping method for robotic navigation. High-quality dense depth maps are estimated and fused into 3D reconstructions in real-time using a single localized moving camera. The quadtree structure of the intensity image is used to reduce the computation burden by estimating the depth map in multiple resolutions. Both the quadtree-based pixel selection and the dynamic belief propagation are proposed to speed up the mapping process: pixels are selected and optimized with the computation resource according to their levels in the quadtree. Solved depth estimations are further interpolated and fused temporally into full resolution depth maps and fused into dense 3D maps using truncated signed distance function (TSDF). We compare our method with other state-of-the-art methods using the public datasets. Onboard UAV autonomous flight is also used to further prove the usability and efficiency of our method on portable devices. For the benefit of the community, the implementation is also released as open source at https://github.com/HKUST-Aerial-Robotics/open_quadtree_mapping.

In content-centric wireless networks, physical layer (PHY) caching has been proposed to exploit the dynamic side information induced by base station (BS) cache to support Coordinated Multi-Point (CoMP) and achieve huge capacity gain. The performance of PHY caching depends heavily on the cache content placement algorithm. In existing algorithms, the cache content placement is adaptive to the long-term popularity distribution in an offline manner. We propose an online PHY caching framework based on the concept of virtual interest packet (VIP) in a virtual network. The VIP captures microscopic spatial and temporary popularity variations, and thus the VIP-based online PHY caching can adapt the cached content to the microscopic popularity variations to fully exploit the benefits of PHY caching. The joint optimization of online caching and content delivery is formulated as a mixed timescale drift minimization problem and a low complexity algorithm is proposed to find the optimal solution. Simulations show that the proposed solution achieves large gain over existing solutions.