Cheng Hu

Zhiping Wu, Cheng Hu, Yiqin Wang et al.

Operating autonomous vehicles at the absolute limits of handling requires precise, real-time identification of highly non-linear tire dynamics. However, traditional online optimization methods suffer from "cold-start" initialization failures and struggle to model high-frequency transient dynamics. To address these bottlenecks, this paper proposes a novel vision-augmented, iterative system identification framework. First, a lightweight CNN (MobileNetV3) translates visual road textures into a continuous heuristic friction prior, providing a robust "warm-start" for parameter optimization. Next, a S4 model captures complex temporal dynamic residuals, circumventing the memory and latency limitations of traditional MLPs and RNNs. Finally, a derivative-free Nelder-Mead algorithm iteratively extracts physically interpretable Pacejka tire parameters via a hybrid virtual simulation. Co-simulation in CarSim demonstrates that the lightweight vision backbone reduces friction estimation error by 76.1 using 85 fewer FLOPs, accelerating cold-start convergence by 71.4. Furthermore, the S4-augmented framework improves parameter extraction accuracy and decreases lateral force RMSE by over 60 by effectively capturing complex vehicle dynamics, demonstrating superior performance compared to conventional neural architectures.

Mingyi Zhang, Cheng Hu, Yiqin Wang et al.

High-speed multi-agent autonomous racing demands robust spatiotemporal planning and precise control under strict computational limits. Current methods often oversimplify interactions or abandon strict kinematic constraints. We resolve this by proposing a Topological Gap Identification and Accelerated MPC framework. By predicting opponent behaviors via SGPs, our method constructs dynamic occupancy corridors to robustly select optimal overtaking gaps. We ensure strict kinematic feasibility using a Linear Time-Varying MPC powered by a customized Pseudo-Transient Continuation (PTC) solver for high-frequency execution. Experimental results on the F1TENTH platform show that our method significantly outperforms state-of-the-art baselines: it reduces total maneuver time by 51.6% in sequential scenarios, consistently maintains an overtaking success rate exceeding 81% in dense bottlenecks, and lowers average computational latency by 20.3%, pushing the boundaries of safe and high-speed autonomous racing.

Zhenjie Xu, Wenqing Chen, Yi Tang et al.

Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially biased outputs. Recent studies have mainly addressed this problem by prompting LLMs to behave ethically, but this approach results in unacceptable performance degradation. In this paper, we propose a multi-objective approach within a multi-agent framework (MOMA) to mitigate social bias in LLMs without significantly compromising their performance. The key idea of MOMA involves deploying multiple agents to perform causal interventions on bias-related contents of the input questions, breaking the shortcut connection between these contents and the corresponding answers. Unlike traditional debiasing techniques leading to performance degradation, MOMA substantially reduces bias while maintaining accuracy in downstream tasks. Our experiments conducted on two datasets and two models demonstrate that MOMA reduces bias scores by up to 87.7%, with only a marginal performance degradation of up to 6.8% in the BBQ dataset. Additionally, it significantly enhances the multi-objective metric icat in the StereoSet dataset by up to 58.1%. Code will be made available at https://github.com/Cortantse/MOMA.

Edoardo Ghignone, Nicolas Baumann, Cheng Hu et al.

Autonomous racing presents a complex environment requiring robust controllers capable of making rapid decisions under dynamic conditions. While traditional controllers based on tire models are reliable, they often demand extensive tuning or system identification. Reinforcement Learning (RL) methods offer significant potential due to their ability to learn directly from interaction, yet they typically suffer from the sim-to-real gap, where policies trained in simulation fail to perform effectively in the real world. In this paper, we propose RLPP, a residual RL framework that enhances a Pure Pursuit (PP) controller with an RL-based residual. This hybrid approach leverages the reliability and interpretability of PP while using RL to fine-tune the controller's performance in real-world scenarios. Extensive testing on the F1TENTH platform demonstrates that RLPP improves lap times of the baseline controllers by up to 6.37 %, closing the gap to the State-of-the-Art methods by more than 52 % and providing reliable performance in zero-shot real-world deployment, overcoming key challenges associated with the sim-to-real transfer and reducing the performance gap from simulation to reality by more than 8-fold when compared to the baseline RL controller. The RLPP framework is made available as an open-source tool, encouraging further exploration and advancement in autonomous racing research. The code is available at: www.github.com/forzaeth/rlpp.

Chenxu Wang, Yonggang Jin, Cheng Hu et al.

Adapting a single agent to a new multi-agent system brings challenges, necessitating adjustments across various tasks, environments, and interactions with unknown teammates and opponents. Addressing this challenge is highly complex, and researchers have proposed two simplified scenarios, Multi-agent reinforcement learning for zero-shot learning and Ad-Hoc Teamwork. Building on these foundations, we propose a more comprehensive setting, Agent Collaborative-Competitive Adaptation (ACCA), which evaluates an agent to generalize across diverse scenarios, tasks, and interactions with both unfamiliar opponents and teammates. In ACCA, agents adjust to task and environmental changes, collaborate with unseen teammates, and compete against unknown opponents. We introduce a new modeling approach, Multi-Retrieval and Dynamic Generation (MRDG), that effectively models both teammates and opponents using their behavioral trajectories. This method incorporates a positional encoder for varying team sizes and a hypernetwork module to boost agents' learning and adaptive capabilities. Additionally, a viewpoint alignment module harmonizes the observational perspectives of retrieved teammates and opponents with the learning agent. Extensive tests in benchmark scenarios like SMAC, Overcooked-AI, and Melting Pot show that MRDG significantly improves robust collaboration and competition with unseen teammates and opponents, surpassing established baselines. Our code is available at: https://github.com/vcis-wangchenxu/MRDG.git

Lin Liu, Jian Zhao, Cheng Hu et al.

Games are widely used as research environments for multi-agent reinforcement learning (MARL), but they pose three significant challenges: limited customization, high computational demands, and oversimplification. To address these issues, we introduce the first publicly available map editor for the popular mobile game Honor of Kings and design a lightweight environment, Mini Honor of Kings (Mini HoK), for researchers to conduct experiments. Mini HoK is highly efficient, allowing experiments to be run on personal PCs or laptops while still presenting sufficient challenges for existing MARL algorithms. We have tested our environment on common MARL algorithms and demonstrated that these algorithms have yet to find optimal solutions within this environment. This facilitates the dissemination and advancement of MARL methods within the research community. Additionally, we hope that more researchers will leverage the Honor of Kings map editor to develop innovative and scientifically valuable new maps. Our code and user manual are available at: https://github.com/tencent-ailab/mini-hok.

Heng Chang, Liang Gu, Cheng Hu et al. · salesforce

Cross-domain recommendation (CDR) is a task that aims to improve the recommendation performance in a target domain by leveraging the information from source domains. Contrastive learning methods have been widely adopted among intra-domain (intra-CL) and inter-domain (inter-CL) users/items for their representation learning and knowledge transfer during the matching stage of CDR. However, we observe that directly employing contrastive learning on mixed-up intra-CL and inter-CL tasks ignores the difficulty of learning from inter-domain over learning from intra-domain, and thus could cause severe training instability. Therefore, this instability deteriorates the representation learning process and hurts the quality of generated embeddings. To this end, we propose a novel framework named SCCDR built up on a separated intra-CL and inter-CL paradigm and a stop-gradient operation to handle the drawback. Specifically, SCCDR comprises two specialized curriculum stages: intra-inter separation and inter-domain curriculum scheduling. The former stage explicitly uses two distinct contrastive views for the intra-CL task in the source and target domains, respectively. Meanwhile, the latter stage deliberately tackles the inter-CL tasks with a curriculum scheduling strategy that derives effective curricula by accounting for the difficulty of negative samples anchored by overlapping users. Empirical experiments on various open-source datasets and an offline proprietary industrial dataset extracted from a real-world recommender system, and an online A/B test verify that SCCDR achieves state-of-the-art performance over multiple baselines.

Nicolas Baumann, Cheng Hu, Paviththiren Sivasothilingam et al.

Neural Networks (NNs) trained through supervised learning struggle with managing edge-case scenarios common in real-world driving due to the intractability of exhaustive datasets covering all edge-cases, making knowledge-driven approaches, akin to how humans intuitively detect unexpected driving behavior, a suitable complement to data-driven methods. This work proposes a hybrid architecture combining low-level Model Predictive Controller (MPC) with locally deployed Large Language Models (LLMs) to enhance decision-making and Human Machine Interaction (HMI). The DecisionxLLM module evaluates robotic state information against natural language instructions to ensure adherence to desired driving behavior. The MPCxLLM module then adjusts MPC parameters based on LLM-generated insights, achieving control adaptability while preserving the safety and constraint guarantees of traditional MPC systems. Further, to enable efficient on-board deployment and to eliminate dependency on cloud connectivity, we shift processing to the on-board computing platform: We propose an approach that exploits Retrieval Augmented Generation (RAG), Low Rank Adaptation (LoRA) fine-tuning, and quantization. Experimental results demonstrate that these enhancements yield significant improvements in reasoning accuracy by up to 10.45%, control adaptability by as much as 52.2%, and up to 10.5x increase in computational efficiency (tokens/s), validating the proposed framework's practicality for real-time deployment even on down-scaled robotic platforms. This work bridges high-level decision-making with low-level control adaptability, offering a synergistic framework for knowledge-driven and adaptive Autonomous Driving Systems (ADS).

Yu Liu, Wenxiao Zhang, Cong Cao et al.

Retrieval-augmented generation (RAG) is widely used to ground Large Language Models (LLMs) for multi-hop question answering. Recent work mainly focused on improving answer accuracy via fine-tuning and structured or reinforcement-based optimization. However, reliable reasoning in response generation faces three challenges: 1) Reasoning Collapse. Reasoning in multi-hop QA is inherently complex due to multi-hop composition and is further destabilized by noisy retrieval. 2) Reasoning-answer inconsistency. Due to the intrinsic uncertainty of LLM generation and exposure to evidence--distractor mixtures, models may produce correct answers that are not faithfully supported by their intermediate reasoning or evidence. 3) Loss of format control. Traditional chain-of-thought generation often deviates from required structured output formats, leading to incomplete or malformed structured content. To address these challenges, we propose CRAFT (Calibrated Reasoning with Answer-Faithful Traces), a Group Relative Policy Optimization (GRPO) based reinforcement learning framework that trains models to perform faithful reasoning during response generation. CRAFT employs dual reward mechanisms to optimize multi-hop reasoning: deterministic rewards ensure structural correctness while judge-based rewards verify semantic faithfulness. This optimization framework supports controllable trace variants that enable systematic analysis of how structure and scale affect reasoning performance and faithfulness. Experiments on three multi-hop QA benchmarks show that CRAFT improves both answer accuracy and reasoning faithfulness across model scales, with the CRAFT 7B model achieving competitive performance with closed-source LLMs across multiple reasoning trace settings.

Haotong Qin, Cheng Hu, Michele Magno

Large Language Model (LLM)-based Vision-Language Models (VLMs) have substantially extended the boundaries of visual understanding capabilities. However, their high computational demands hinder deployment on resource-constrained edge devices. A key source of inefficiency stems from the VLM's need to process dense and redundant visual information. Visual inputs contain significant regions irrelevant to text semantics, rendering the associated computations ineffective for inference. This paper introduces a novel Event-Priori-Based Vision-Language Model, termed EP-VLM. Its core contribution is a novel mechanism leveraging motion priors derived from dynamic event vision to enhance VLM efficiency. Inspired by human visual cognition, EP-VLM first employs event data to guide the patch-wise sparsification of RGB visual inputs, progressively concentrating VLM computation on salient regions of the visual input. Subsequently, we construct a position-preserving tokenization strategy for the visual encoder within the VLM architecture. This strategy processes the event-guided, unstructured, sparse visual input while accurately preserving positional understanding within the visual input. Experimental results demonstrate that EP-VLM achieves significant efficiency improvements while maintaining nearly lossless accuracy compared to baseline models from the Qwen2-VL series. For instance, against the original Qwen2-VL-2B, EP-VLM achieves 50% FLOPs savings while retaining 98% of the original accuracy on the RealWorldQA dataset. This work demonstrates the potential of event-based vision priors for improving VLM inference efficiency, paving the way for creating more efficient and deployable VLMs for sustainable visual understanding at the edge.

Qinbing Fu, Tian Liu, Xuelong Sun et al.

Visual dynamic complexity is a ubiquitous, hidden attribute of the visual world that every dynamic vision system is faced with. However, it is implicit and intractable which has never been quantitatively described due to the difficulty in defending temporal features correlated to spatial image complexity. To fill this vacancy, we propose a novel bio-robotic approach to profile visual dynamic complexity which can be used as a new metric. Here we apply a state-of-the-art brain-inspired motion detection neural network model to explicitly profile such complexity associated with spatial-temporal frequency (SF-TF) of visual scene. This model is for the first time implemented in an autonomous micro-mobile robot which navigates freely in an arena with visual walls displaying moving sine-wave grating or cluttered natural scene. The neural dynamic response can make reasonable prediction on surrounding complexity since it can be mapped monotonically to varying SF-TF of visual scene. The experiments show this approach is flexible to different visual scenes for profiling the dynamic complexity. We also use this metric as a predictor to investigate the boundary of another collision detection visual system performing in changing environment with increasing dynamic complexity. This research demonstrates a new paradigm of using biologically plausible visual processing scheme to estimate dynamic complexity of visual scene from both spatial and temporal perspectives, which could be beneficial to predicting input complexity when evaluating dynamic vision systems.

Hongxin Wang, Jiannan Zhao, Huatian Wang et al.

Small target motion detection within complex natural environments is an extremely challenging task for autonomous robots. Surprisingly, the visual systems of insects have evolved to be highly efficient in detecting mates and tracking prey, even though targets occupy as small as a few degrees of their visual fields. The excellent sensitivity to small target motion relies on a class of specialized neurons called small target motion detectors (STMDs). However, existing STMD-based models are heavily dependent on visual contrast and perform poorly in complex natural environments where small targets generally exhibit extremely low contrast against neighbouring backgrounds. In this paper, we develop an attention and prediction guided visual system to overcome this limitation. The developed visual system comprises three main subsystems, namely, an attention module, an STMD-based neural network, and a prediction module. The attention module searches for potential small targets in the predicted areas of the input image and enhances their contrast against complex background. The STMD-based neural network receives the contrast-enhanced image and discriminates small moving targets from background false positives. The prediction module foresees future positions of the detected targets and generates a prediction map for the attention module. The three subsystems are connected in a recurrent architecture allowing information to be processed sequentially to activate specific areas for small target detection. Extensive experiments on synthetic and real-world datasets demonstrate the effectiveness and superiority of the proposed visual system for detecting small, low-contrast moving targets against complex natural environments.

Hongxin Wang, Huatian Wang, Jiannan Zhao et al.

Discriminating small moving objects within complex visual environments is a significant challenge for autonomous micro robots that are generally limited in computational power. By exploiting their highly evolved visual systems, flying insects can effectively detect mates and track prey during rapid pursuits, even though the small targets equate to only a few pixels in their visual field. The high degree of sensitivity to small target movement is supported by a class of specialized neurons called small target motion detectors (STMDs). Existing STMD-based computational models normally comprise four sequentially arranged neural layers interconnected via feedforward loops to extract information on small target motion from raw visual inputs. However, feedback, another important regulatory circuit for motion perception, has not been investigated in the STMD pathway and its functional roles for small target motion detection are not clear. In this paper, we propose an STMD-based neural network with feedback connection (Feedback STMD), where the network output is temporally delayed, then fed back to the lower layers to mediate neural responses. We compare the properties of the model with and without the time-delay feedback loop, and find it shows preference for high-velocity objects. Extensive experiments suggest that the Feedback STMD achieves superior detection performance for fast-moving small targets, while significantly suppressing background false positive movements which display lower velocities. The proposed feedback model provides an effective solution in robotic visual systems for detecting fast-moving small targets that are always salient and potentially threatening.

Xuelong Sun, Tian Liu, Cheng Hu et al.

In the last few decades we have witnessed how the pheromone of social insect has become a rich inspiration source of swarm robotics. By utilising the virtual pheromone in physical swarm robot system to coordinate individuals and realise direct/indirect inter-robot communications like the social insect, stigmergic behaviour has emerged. However, many studies only take one single pheromone into account in solving swarm problems, which is not the case in real insects. In the real social insect world, diverse behaviours, complex collective performances and flexible transition from one state to another are guided by different kinds of pheromones and their interactions. Therefore, whether multiple pheromone based strategy can inspire swarm robotics research, and inversely how the performances of swarm robots controlled by multiple pheromones bring inspirations to explain the social insects' behaviours will become an interesting question. Thus, to provide a reliable system to undertake the multiple pheromone study, in this paper, we specifically proposed and realised a multiple pheromone communication system called ColCOS$Φ$. This system consists of a virtual pheromone sub-system wherein the multiple pheromone is represented by a colour image displayed on a screen, and the micro-robots platform designed for swarm robotics applications. Two case studies are undertaken to verify the effectiveness of this system: one is the multiple pheromone based on an ant's forage and another is the interactions of aggregation and alarm pheromones. The experimental results demonstrate the feasibility of ColCOS$Φ$ and its great potential in directing swarm robotics and social insects research.

Jiannan Zhao, Xingzao Ma, Qinbing Fu et al.

Building a reliable and efficient collision avoidance system for unmanned aerial vehicles (UAVs) is still a challenging problem. This research takes inspiration from locusts, which can fly in dense swarms for hundreds of miles without collision. In the locust's brain, a visual pathway of LGMD-DCMD (lobula giant movement detector and descending contra-lateral motion detector) has been identified as collision perception system guiding fast collision avoidance for locusts, which is ideal for designing artificial vision systems. However, there is very few works investigating its potential in real-world UAV applications. In this paper, we present an LGMD based competitive collision avoidance method for UAV indoor navigation. Compared to previous works, we divided the UAV's field of view into four subfields each handled by an LGMD neuron. Therefore, four individual competitive LGMDs (C-LGMD) compete for guiding the directional collision avoidance of UAV. With more degrees of freedom compared to ground robots and vehicles, the UAV can escape from collision along four cardinal directions (e.g. the object approaching from the left-side triggers a rightward shifting of the UAV). Our proposed method has been validated by both simulations and real-time quadcopter arena experiments.

Qinbing Fu, Cheng Hu, Pengcheng Liu et al.

Insects have tiny brains but complicated visual systems for motion perception. A handful of insect visual neurons have been computationally modeled and successfully applied for robotics. How different neurons collaborate on motion perception, is an open question to date. In this paper, we propose a novel embedded vision system in autonomous micro-robots, to recognize motion patterns in dynamic robot scenes. Here, the basic motion patterns are categorized into movements of looming (proximity), recession, translation, and other irrelevant ones. The presented system is a synthetic neural network, which comprises two complementary sub-systems with four spiking neurons -- the lobula giant movement detectors (LGMD1 and LGMD2) in locusts for sensing looming and recession, and the direction selective neurons (DSN-R and DSN-L) in flies for translational motion extraction. Images are transformed to spikes via spatiotemporal computations towards a switch function and decision making mechanisms, in order to invoke proper robot behaviors amongst collision avoidance, tracking and wandering, in dynamic robot scenes. Our robot experiments demonstrated two main contributions: (1) This neural vision system is effective to recognize the basic motion patterns corresponding to timely and proper robot behaviors in dynamic scenes. (2) The arena tests with multi-robots demonstrated the effectiveness in recognizing more abundant motion features for collision detection, which is a great improvement compared with former studies.

Qinbing Fu, Hongxin Wang, Cheng Hu et al.

Motion perception is a critical capability determining a variety of aspects of insects' life, including avoiding predators, foraging and so forth. A good number of motion detectors have been identified in the insects' visual pathways. Computational modelling of these motion detectors has not only been providing effective solutions to artificial intelligence, but also benefiting the understanding of complicated biological visual systems. These biological mechanisms through millions of years of evolutionary development will have formed solid modules for constructing dynamic vision systems for future intelligent machines. This article reviews the computational motion perception models originating from biological research of insects' visual systems in the literature. These motion perception models or neural networks comprise the looming sensitive neuronal models of lobula giant movement detectors (LGMDs) in locusts, the translation sensitive neural systems of direction selective neurons (DSNs) in fruit flies, bees and locusts, as well as the small target motion detectors (STMDs) in dragonflies and hover flies. We also review the applications of these models to robots and vehicles. Through these modelling studies, we summarise the methodologies that generate different direction and size selectivity in motion perception. At last, we discuss about multiple systems integration and hardware realisation of these bio-inspired motion perception models.

Jiannan Zhao, Cheng Hu, Chun Zhang et al.

Sense and avoid capability enables insects to fly versatilely and robustly in dynamic complex environment. Their biological principles are so practical and efficient that inspired we human imitating them in our flying machines. In this paper, we studied a novel bio-inspired collision detector and its application on a quadcopter. The detector is inspired from LGMD neurons in the locusts, and modeled into an STM32F407 MCU. Compared to other collision detecting methods applied on quadcopters, we focused on enhancing the collision selectivity in a bio-inspired way that can considerably increase the computing efficiency during an obstacle detecting task even in complex dynamic environment. We designed the quadcopter's responding operation imminent collisions and tested this bio-inspired system in an indoor arena. The observed results from the experiments demonstrated that the LGMD collision detector is feasible to work as a vision module for the quadcopter's collision avoidance task.

Qinbing Fu, Cheng Hu, Shigang Yue

For autonomous robots in dynamic environments mixed with human, it is vital to detect impending collision quickly and robustly. The biological visual systems evolved over millions of years may provide us efficient solutions for collision detection in complex environments. In the cockpit of locusts, two Lobula Giant Movement Detectors, i.e. LGMD1 and LGMD2, have been identified which respond to looming objects rigorously with high firing rates. Compared to LGMD1, LGMD2 matures early in the juvenile locusts with specific selectivity to dark moving objects against bright background in depth while not responding to light objects embedded in dark background - a similar situation which ground vehicles and robots are facing with. However, little work has been done on modeling LGMD2, let alone its potential in robotics and other vision-based applications. In this article, we propose a novel way of modeling LGMD2 neuron, with biased ON and OFF pathways splitting visual streams into parallel channels encoding brightness increments and decrements separately to fulfill its selectivity. Moreover, we apply a biophysical mechanism of spike frequency adaptation to shape the looming selectivity in such a collision-detecting neuron model. The proposed visual neural network has been tested with systematic experiments, challenged against synthetic and real physical stimuli, as well as image streams from the sensor of a miniature robot. The results demonstrated this framework is able to detect looming dark objects embedded in bright backgrounds selectively, which make it ideal for ground mobile platforms. The robotic experiments also showed its robustness in collision detection - it performed well for near range navigation in an arena with many obstacles. Its enhanced collision selectivity to dark approaching objects versus receding and translating ones has also been verified via systematic experiments.