Alois Knoll

AAAI Conference 2026 Conference Paper

OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model

• Xingcheng Zhou
• Xuyuan Han
• Feng Yang
• Yunpu Ma
• Volker Tresp
• Alois Knoll

We present OpenDriveVLA, a Vision-Language Action (VLA) model designed for end-to-end autonomous driving, built upon open-source large language models. OpenDriveVLA generates spatially-grounded driving actions by leveraging multimodal inputs, including both 2D and 3D instance-aware visual representations, ego vehicle states, and language commands. To bridge the modality gap between driving visual representations and language embeddings, we introduce a hierarchical vision-language alignment process, projecting both 2D and 3D structured visual tokens into a unified semantic space. Furthermore, we incorporate structured agent–environment–ego interaction modeling into the autoregressive decoding process, enabling the model to capture fine-grained spatial dependencies and behavior-aware dynamics critical for reliable trajectory planning. Extensive experiments on the nuScenes dataset demonstrate that OpenDriveVLA achieves state-of-the-art results across open-loop trajectory planning and driving-related question-answering tasks. Qualitative analyses further illustrate its superior capability to follow high-level driving commands and robustly generate trajectories under challenging scenarios, highlighting its potential for next-generation end-to-end autonomous driving.

NeurIPS Conference 2025 Conference Paper

Bio-Inspired Image Restoration

• Yuning Cui
• Wenqi Ren
• Alois Knoll

Image restoration aims to recover sharp, high-quality images from degraded, low-quality inputs. Existing methods have progressively advanced from task-specific designs to general architectures, all-in-one frameworks, and composite degradation handling. Despite these advances, computational efficiency remains a critical factor for practical deployment. In this work, we present BioIR, an efficient and universal image restoration framework inspired by the human visual system. Specifically, we design two bio-inspired modules, Peripheral-to-Foveal (P2F) and Foveal-to-Peripheral (F2P), to emulate the perceptual processes of human vision, with a particular focus on the functional interplay between foveal and peripheral pathways. P2F delivers large-field contextual signals to foveal regions based on pixel-to-region affinity, while F2P propagates fine-grained spatial details through a static-to-dynamic two-stage integration strategy. Leveraging the biologically motivated design, BioIR achieves state-of-the-art performance across three representative image restoration settings: single-degradation, all-in-one, and composite degradation. Moreover, BioIR maintains high computational efficiency and fast inference speed, making it highly suitable for real-world applications.

AAAI Conference 2024 Conference Paper

Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation

• Shangding Gu
• Bilgehan Sel
• Yuhao Ding
• Lu Wang
• Qingwei Lin
• Ming Jin
• Alois Knoll

Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications. Nevertheless, managing the trade-off between reward and safety during exploration presents a significant challenge. Improving reward performance through policy adjustments may adversely affect safety performance. In this study, we aim to address this conflicting relation by leveraging the theory of gradient manipulation. Initially, we analyze the conflict between reward and safety gradients. Subsequently, we tackle the balance between reward and safety optimization by proposing a soft switching policy optimization method, for which we provide convergence analysis. Based on our theoretical examination, we provide a safe RL framework to overcome the aforementioned challenge, and we develop a Safety-MuJoCo Benchmark to assess the performance of safe RL algorithms. Finally, we evaluate the effectiveness of our method on the Safety-MuJoCo Benchmark and a popular safe benchmark, Omnisafe. Experimental results demonstrate that our algorithms outperform several state-of-the-art baselines in terms of balancing reward and safety optimization.

NeurIPS Conference 2024 Conference Paper

Diffusion-based Curriculum Reinforcement Learning

• Erdi Sayar
• Giovanni Iacca
• Ozgur S. Oguz
• Alois Knoll

Curriculum Reinforcement Learning (CRL) is an approach to facilitate the learning process of agents by structuring tasks in a sequence of increasing complexity. Despite its potential, many existing CRL methods struggle to efficiently guide agents toward desired outcomes, particularly in the absence of domain knowledge. This paper introduces DiCuRL (Diffusion Curriculum Reinforcement Learning), a novel method that leverages conditional diffusion models to generate curriculum goals. To estimate how close an agent is to achieving its goal, our method uniquely incorporates a $Q$-function and a trainable reward function based on Adversarial Intrinsic Motivation within the diffusion model. Furthermore, it promotes exploration through the inherent noising and denoising mechanism present in the diffusion models and is environment-agnostic. This combination allows for the generation of challenging yet achievable goals, enabling agents to learn effectively without relying on domain knowledge. We demonstrate the effectiveness of DiCuRL in three different maze environments and two robotic manipulation tasks simulated in MuJoCo, where it outperforms or matches nine state-of-the-art CRL algorithms from the literature.

NeurIPS Conference 2024 Conference Paper

Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation

• Shangding Gu
• Laixi Shi
• Yuhao Ding
• Alois Knoll
• Costas Spanos
• Adam Wierman
• Ming Jin

Safe reinforcement learning (RL) is crucial for deploying RL agents in real-world applications, as it aims to maximize long-term rewards while satisfying safety constraints. However, safe RL often suffers from sample inefficiency, requiring extensive interactions with the environment to learn a safe policy. We propose Efficient Safe Policy Optimization (ESPO), a novel approach that enhances the efficiency of safe RL through sample manipulation. ESPO employs an optimization framework with three modes: maximizing rewards, minimizing costs, and balancing the trade-off between the two. By dynamically adjusting the sampling process based on the observed conflict between reward and safety gradients, ESPO theoretically guarantees convergence, optimization stability, and improved sample complexity bounds. Experiments on the Safety-MuJoCo and Omnisafe benchmarks demonstrate that ESPO significantly outperforms existing primal-based and primal-dual-based baselines in terms of reward maximization and constraint satisfaction. Moreover, ESPO achieves substantial gains in sample efficiency, requiring 25--29\% fewer samples than baselines, and reduces training time by 21--38\%.

IJCAI Conference 2024 Conference Paper

Hybrid Frequency Modulation Network for Image Restoration

• Yuning Cui
• Mingyu Liu
• Wenqi Ren
• Alois Knoll

Image restoration involves recovering a high-quality image from its corrupted counterpart. This paper presents an effective and efficient framework for image restoration, termed CSNet, based on ``channel + spatial" hybrid frequency modulation. Different feature channels include different degradation patterns and degrees, however, most current networks ignore the importance of channel interactions. To alleviate this issue, we propose a frequency-based channel feature modulation module to facilitate channel interactions through the channel-dimension Fourier transform. Furthermore, based on our observations, we develop a multi-scale frequency-based spatial feature modulation module to refine the direct-current component of features using extremely lightweight learnable parameters. This module contains a densely connected coarse-to-fine learning paradigm for enhancing multi-scale representation learning. In addition, we introduce a frequency-inspired loss function to achieve omni-frequency learning. Extensive experiments on nine datasets demonstrate that the proposed network achieves state-of-the-art performance for three image restoration tasks, including image dehazing, image defocus deblurring, and image desnowing. The code and models are available at https: //github. com/c-yn/CSNet.

AAAI Conference 2024 Conference Paper

Omni-Kernel Network for Image Restoration

• Yuning Cui
• Wenqi Ren
• Alois Knoll

Image restoration aims to reconstruct a high-quality image from a degraded low-quality observation. Recently, Transformer models have achieved promising performance on image restoration tasks due to their powerful ability to model long-range dependencies. However, the quadratically growing complexity with respect to the input size makes them inapplicable to practical applications. In this paper, we develop an efficient convolutional network for image restoration by enhancing multi-scale representation learning. To this end, we propose an omni-kernel module that consists of three branches, i.e., global, large, and local branches, to learn global-to-local feature representations efficiently. Specifically, the global branch achieves a global perceptive field via the dual-domain channel attention and frequency-gated mechanism. Furthermore, to provide multi-grained receptive fields, the large branch is formulated via different shapes of depth-wise convolutions with unusually large kernel sizes. Moreover, we complement local information using a point-wise depth-wise convolution. Finally, the proposed network, dubbed OKNet, is established by inserting the omni-kernel module into the bottleneck position for efficiency. Extensive experiments demonstrate that our network achieves state-of-the-art performance on 11 benchmark datasets for three representative image restoration tasks, including image dehazing, image desnowing, and image defocus deblurring. The code is available at https://github.com/c-yn/OKNet.

TMLR Journal 2024 Journal Article

TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning

• Shangding Gu
• Alois Knoll
• Ming Jin

The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries tied to the self-instruct paradigm. In this work, we pivot to Reinforcement Learning (RL)---but with a twist. Diverging from the typical RLHF, which refines LLMs following instruction data training, we use RL to directly generate the foundational instruction dataset that alone suffices for fine-tuning. Our method, TeaMs-RL, uses a suite of textual operations and rules, prioritizing the diversification of training datasets. It facilitates the generation of high-quality data without excessive reliance on external advanced models, paving the way for a single fine-tuning step and negating the need for subsequent RLHF stages. Our findings highlight key advantages of our approach: reduced need for human involvement and fewer model queries (only $5.73\%$ of the strong baseline's total), along with enhanced capabilities of LLMs in crafting and comprehending complex instructions compared to strong baselines, and substantially improved model privacy protection. Code is available at the link: https://github.com/SafeRL-Lab/TeaMs-RL

AAAI Conference 2023 Conference Paper

Dual-Domain Attention for Image Deblurring

• Yuning Cui
• Yi Tao
• Wenqi Ren
• Alois Knoll

As a long-standing and challenging task, image deblurring aims to reconstruct the latent sharp image from its degraded counterpart. In this study, to bridge the gaps between degraded/sharp image pairs in the spatial and frequency domains simultaneously, we develop the dual-domain attention mechanism for image deblurring. Self-attention is widely used in vision tasks, however, due to the quadratic complexity, it is not applicable to image deblurring with high-resolution images. To alleviate this issue, we propose a novel spatial attention module by implementing self-attention in the style of dynamic group convolution for integrating information from the local region, enhancing the representation learning capability and reducing computational burden. Regarding frequency domain learning, many frequency-based deblurring approaches either treat the spectrum as a whole or decompose frequency components in a complicated manner. In this work, we devise a frequency attention module to compactly decouple the spectrum into distinct frequency parts and accentuate the informative part with extremely lightweight learnable parameters. Finally, we incorporate attention modules into a U-shaped network. Extensive comparisons with prior arts on the common benchmarks show that our model, named Dual-domain Attention Network (DDANet), obtains comparable results with a significantly improved inference speed.

AAAI Conference 2023 Conference Paper

Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning

• Mingyang Wang
• Zhenshan Bing
• Xiangtong Yao
• Shuai Wang
• Huang Kai
• Hang Su
• Chenguang Yang
• Alois Knoll

Meta-reinforcement learning enables artificial agents to learn from related training tasks and adapt to new tasks efficiently with minimal interaction data. However, most existing research is still limited to narrow task distributions that are parametric and stationary, and does not consider out-of-distribution tasks during the evaluation, thus, restricting its application. In this paper, we propose MoSS, a context-based Meta-reinforcement learning algorithm based on Self-Supervised task representation learning to address this challenge. We extend meta-RL to broad non-parametric task distributions which have never been explored before, and also achieve state-of-the-art results in non-stationary and out-of-distribution tasks. Specifically, MoSS consists of a task inference module and a policy module. We utilize the Gaussian mixture model for task representation to imitate the parametric and non-parametric task variations. Additionally, our online adaptation strategy enables the agent to react at the first sight of a task change, thus being applicable in non-stationary tasks. MoSS also exhibits strong generalization robustness in out-of-distributions tasks which benefits from the reliable and robust task representation. The policy is built on top of an off-policy RL algorithm and the entire network is trained completely off-policy to ensure high sample efficiency. On MuJoCo and Meta-World benchmarks, MoSS outperforms prior works in terms of asymptotic performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization robustness on broad and diverse task distributions.

EAAI Journal 2023 Journal Article

Real-time semantic segmentation in traffic scene using Cross Stage Partial-based encoder–decoder network

• Liguo Zhou
• Guang Chen
• Lian Liu
• Ruining Wang
• Alois Knoll

Real-time semantic segmentation in traffic scenes plays an essential part in autonomous driving. The encoder–decoder-based network architecture can well combine the context information and detailed information required for the semantic segmentation task. Achieving a good balance between inference speed and accuracy is a crucial challenge, as considerable real-time semantic segmentation models process information in real-time at the expense of accuracy degradation. This paper presents an encoder–decoder network model based on Cross Stage Partial (CSP) block for real-time semantic segmentation in traffic scenes. Integrating the CSP block can not only lessen the computational overhead but also enhance the feature extraction ability of the network. In addition, we append the Fast Spatial Pyramid Pooling module to the backbone of the network, which can aggregate global information at a low computational cost. On NVIDIA RTX 3090, the middle model of our method can achieve a mean intersection over union (mIOU) of 80. 8% at 64. 3 frames per second (FPS) on the Cityscapes test set and an mIOU of 81. 3% at 105. 3 FPS on the CamVid Test Set. The large model of our method can realize an mIOU of 81. 5% at 48. 4 FPS on the test set of Cityscapes. Our source code is available at https: //github. com/zhouliguo/cspsg.

AIJ Journal 2023 Journal Article

Safe multi-agent reinforcement learning for multi-robot control

• Shangding Gu
• Jakub Grudzien Kuba
• Yuanpei Chen
• Yali Du
• Long Yang
• Alois Knoll
• Yaodong Yang

A challenging problem in robotics is how to control multiple robots cooperatively and safely in real-world applications. Yet, developing multi-robot control methods from the perspective of safe multi-agent reinforcement learning (MARL) has merely been studied. To fill this gap, in this study, we investigate safe MARL for multi-robot control on cooperative tasks, in which each individual robot has to not only meet its own safety constraints while maximising their reward, but also consider those of others to guarantee safe team behaviours. Firstly, we formulate the safe MARL problem as a constrained Markov game and employ policy optimisation to solve it theoretically. The proposed algorithm guarantees monotonic improvement in reward and satisfaction of safety constraints at every iteration. Secondly, as approximations to the theoretical solution, we propose two safe multi-agent policy gradient methods: Multi-Agent Constrained Policy Optimisation (MACPO) and MAPPO-Lagrangian. Thirdly, we develop the first three safe MARL benchmarks—Safe Multi-Agent MuJoCo (Safe MAMuJoCo), Safe Multi-Agent Robosuite (Safe MARobosuite) and Safe Multi-Agent Isaac Gym (Safe MAIG) to expand the toolkit of MARL and robot control research communities. Finally, experimental results on the three safe MARL benchmarks indicate that our methods can achieve state-of-the-art performance in the balance between improving reward and satisfying safety constraints compared with strong baselines. Demos and code are available at the link (https: //sites. google. com/view/aij-safe-marl/). 2

IJCAI Conference 2023 Conference Paper

Strip Attention for Image Restoration

• Yuning Cui
• Yi Tao
• Luoxi Jing
• Alois Knoll

As a long-standing task, image restoration aims to recover the latent sharp image from its degraded counterpart. In recent years, owing to the strong ability of self-attention in capturing long-range dependencies, Transformer based methods have achieved promising performance on multifarious image restoration tasks. However, the canonical self-attention leads to quadratic complexity with respect to input size, hindering its further applications in image restoration. In this paper, we propose a Strip Attention Network (SANet) for image restoration to integrate information in a more efficient and effective manner. Specifically, a strip attention unit is proposed to harvest the contextual information for each pixel from its adjacent pixels in the same row or column. By employing this operation in different directions, each location can perceive information from an expanded region. Furthermore, we apply various receptive fields in different feature groups to enhance representation learning. Incorporating these designs into a U-shaped backbone, our SANet performs favorably against state-of-the-art algorithms on several image restoration tasks. The code is available at https: //github. com/c-yn/SANet.

AAAI Conference 2021 Conference Paper

PointINet: Point Cloud Frame Interpolation Network

• Fan Lu
• Guang Chen
• Sanqing Qu
• Zhijun Li
• Yinlong Liu
• Alois Knoll

LiDAR point cloud streams are usually sparse in time dimension, which is limited by hardware performance. Generally, the frame rates of mechanical LiDAR sensors are 10 to 20 Hz, which is much lower than other commonly used sensors like cameras. To overcome the temporal limitations of LiDAR sensors, a novel task named Point Cloud Frame Interpolation is studied in this paper. Given two consecutive point cloud frames, Point Cloud Frame Interpolation aims to generate intermediate frame(s) between them. To achieve that, we propose a novel framework, namely Point Cloud Frame Interpolation Network (PointINet). Based on the proposed method, the low frame rate point cloud streams can be upsampled to higher frame rates. We start by estimating bi-directional 3D scene flow between the two point clouds and then warp them to the given time step based on the 3D scene flow. To fuse the two warped frames and generate intermediate point cloud(s), we propose a novel learning-based points fusion module, which simultaneously takes two warped point clouds into consideration. We design both quantitative and qualitative experiments to evaluate the performance of the point cloud frame interpolation method and extensive experiments on two large scale outdoor LiDAR datasets demonstrate the effectiveness of the proposed PointINet. Our code is available at https: //github. com/ispc-lab/PointINet. git.

NeurIPS Conference 2020 Conference Paper

RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor

• Fan Lu
• Guang Chen
• Yinlong Liu
• Zhongnan Qu
• Alois Knoll

Keypoint detector and descriptor are two main components of point cloud registration. Previous learning-based keypoint detectors rely on saliency estimation for each point or farthest point sample (FPS) for candidate points selection, which are inefficient and not applicable in large scale scenes. This paper proposes Random Sample-based Keypoint Detector and Descriptor Network (RSKDD-Net) for large scale point cloud registration. The key idea is using random sampling to efficiently select candidate points and using a learning-based method to jointly generate keypoints and corresponding descriptors. To tackle the information loss of random sampling, we exploit a novel random dilation cluster strategy to enlarge the receptive field of each sampled point and an attention mechanism to aggregate the positions and features of neighbor points. Furthermore, we propose a matching loss to train the descriptor in a weakly supervised manner. Extensive experiments on two large scale outdoor LiDAR datasets show that the proposed RSKDD-Net achieves state-of-the-art performance with more than 15 times faster than existing methods. Our code is available at https: //github. com/ispc-lab/RSKDD-Net.

IJCAI Conference 2019 Conference Paper

Energy-Efficient Slithering Gait Exploration for a Snake-Like Robot Based on Reinforcement Learning

• Zhenshan Bing
• Christian Lemke
• Zhuangyi Jiang
• Kai Huang
• Alois Knoll

Similar to their counterparts in nature, the flexible bodies of snake-like robots enhance their movement capability and adaptability in diverse environments. However, this flexibility corresponds to a complex control task involving highly redundant degrees of freedom, where traditional model-based methods usually fail to propel the robots energy-efficiently. In this work, we present a novel approach for designing an energy-efficient slithering gait for a snake-like robot using a model-free reinforcement learning (RL) algorithm. Specifically, we present an RL-based controller for generating locomotion gaits at a wide range of velocities, which is trained using the proximal policy optimization (PPO) algorithm. Meanwhile, a traditional parameterized gait controller is presented and the parameter sets are optimized using the grid search and Bayesian optimization algorithms for the purposes of reasonable comparisons. Based on the analysis of the simulation results, we demonstrate that this RL-based controller exhibits very natural and adaptive movements, which are also substantially more energy-efficient than the gaits generated by the parameterized controller. Videos are shown at https: //videoviewsite. wixsite. com/rlsnake.

JAIR Journal 2018 Journal Article

KABouM: Knowledge-Level Action and Bounding Geometry Motion Planner

• Andre Gaschler
• Ronald P. A. Petrick
• Oussama Khatib
• Alois Knoll

For robots to solve real world tasks, they often require the ability to reason about both symbolic and geometric knowledge. We present a framework, called KABouM, for integrating knowledge-level task planning and motion planning in a bounding geometry. By representing symbolic information at the knowledge level, we can model incomplete information, sensing actions and information gain; by representing all geometric entities--objects, robots and swept volumes of motions--by sets of convex polyhedra, we can efficiently plan manipulation actions and raise reasoning about geometric predicates, such as collisions, to the symbolic level. At the geometric level, we take advantage of our bounded convex decomposition and swept volume computation with quadratic convergence, and fast collision detection of convex bodies. We evaluate our approach on a wide set of problems using real robots, including tasks with multiple manipulators, sensing and branched plans, and mobile manipulation.

IJCAI Conference 2009 Conference Paper

• Mary Ellen Foster
• Manuel Giuliani
• Amy Isard
• Colin Matheson
• Jon Oberlander
• Alois Knoll

We present a human-robot dialogue system that enables a robot to work together with a human user to build wooden construction toys. We then describe a study which assessed the responses of naı̈ve users to output that varied along two dimensions: the method of describing an assembly plan (pre-order or post-order), and the method of referring to objects in the world (basic and full). Varying both of these factors produced significant results: subjects using the system that employed a pre-order description strategy asked for instructions to be repeated significantly less often than those who experienced the post-order strategy, while the subjects who heard references generated by the full reference strategy judged the robot’s instructions to be significantly more understandable than did those who heard the output of the basic strategy.