Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Driving
Jet Propulsion Laboratory, California Institute of Technology（喷气推进实验室、加州理工学院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Georgia Institute of Technology（佐治亚理工学院）
Jacob Levy, Jason Gibson, Bogdan Vlahov, Erica Tevere, Evangelos Theodorou, David Fridovich-Keil, Patrick Spieler
High-speed off-road autonomous driving presents unique challenges due to complex, evolving terrain characteristics and the difficulty of accurately modeling terrain-vehicle interactions. While dynamics models used in model-based control can be learned from real-world data, they often struggle to generalize to unseen terrain, making real-time adaptation essential. We propose a novel framework that combines a Kalman filter-based online adaptation scheme with meta-learned parameters to address these challenges. Offline meta-learning optimizes the basis functions along which adaptation occurs, as well as the adaptation parameters, while online adaptation dynamically adjusts the onboard dynamics model in real time for model-based control. We validate our approach through extensive experiments, including real-world testing on a full-scale autonomous off-road vehicle, demonstrating that our method outperforms baseline approaches in prediction accuracy, performance, and safety metrics, particularly in safety-critical scenarios. Our results underscore the effectiveness of meta-learned dynamics model adaptation, advancing the development of reliable autonomous systems capable of navigating diverse and unseen environments. Video is available at: https://youtu.be/cCKHHrDRQEA
Tianjin University（天津大学）；University of Electronic Science and Technology of China（电子科技大学）；Tianjin University of Traditional Chinese Medicine（天津中医药大学）
Road rage is a social problem that deserves attention, but little research has been done so far. In this paper, based on the biological topology of multi-channel EEG signals,we propose a model which combines transferable attention (TA) and regularized graph neural network (RGNN). First, topology-aware information aggregation is performed on EEG signals, and complex relationships between channels are dynamically learned. Then, the transferability of each channel is quantified based on the results of the node-wise domain classifier, which is used as attention score. We recruited 10 subjects and …
Georgia Institute of Technology（佐治亚理工学院）；Robotics at Google（谷歌机器人部门）
The ability to walk in new scenarios is a key milestone on the path toward real-world applications of legged robots. In this work, we introduce Meta Strategy Optimization, a meta-learning algorithm for training policies with latent variable inputs that can quickly adapt to new scenarios with a handful of trials in the target environment. The key idea behind MSO is to expose the same adaptation process, Strategy Optimization (SO), to both the training and testing phases. This allows MSO to effectively learn locomotion skills as well as a latent space that is suitable for fast adaptation. We eva…
Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters are updated during meta-update. The normal meta-training strategy needs to differentiate through the inner-task adaptation procedure to optimize the meta-parameters. This leads to a constraint that the inner-task algorithms should be solved analytically. Under this constraint, only simple algorithms with analytical solutions can be applied as the inner-task algorithms, limiting the model expressiveness. To lift the …
Saliency-Guided Domain Adaptation for Left-Hand Driving in Autonomous Steering
Centre for Accident Research and Road Safety-Queensland, Queensland University of Technology（昆士兰事故研究与道路安全中心、昆士兰理工大学）；QUT Centre for Robotics and School of Electrical Engineering and Computer Science, Queensland University of Technology（昆士兰大学机器人中心及电气工程与计算机科学学院、昆士兰理工大学）
Russian Quantum Center（俄罗斯量子中心）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；University of Oxford（牛津大学）
Animals have remarkable abilities to adapt locomotion to different terrains and tasks. However, robots trained by means of reinforcement learning are typically able to solve only a single task and a transferred policy is usually inferior to that trained from scratch. In this work, we demonstrate that meta-reinforcement learning can be used to successfully train a robot capable to solve a wide range of locomotion tasks. The performance of the meta-trained robot is similar to that of a robot that is trained on a single task.
Ability to continuously learn and adapt from limited experience in nonstationary environments is an important milestone on the path towards general intelligence. In this paper, we cast the problem of continuous adaptation into the learning-to-learn framework. We develop a simple gradient-based meta-learning algorithm suitable for adaptation in dynamically changing and adversarial scenarios. Additionally, we design a new multi-agent competitive environment, RoboSumo, and define iterated adaptation games for testing various aspects of continuous adaptation strategies. We demonstrate that meta-le…
Neural networks require a large amount of annotated data to learn. Meta-learning algorithms propose a way to decrease the number of training samples to only a few. One of the most prominent optimization-based meta-learning algorithms is Model-Agnostic Meta-Learning (MAML). However, the key procedure of adaptation to new tasks in MAML is quite slow. In this work we propose an improvement to MAML meta-learning algorithm. We introduce Lambda patterns by which we restrict which weight are updated in the network during the adaptation phase. This makes it possible to skip certain gradient computatio…
The University of Melbourne（墨尔本大学）；Monash University（莫纳什大学）
Inspired by the concept of preconditioning, we propose a novel method to increase adaptation speed for gradient-based meta-learning methods without incurring extra parameters. We demonstrate that recasting the optimization problem to a non-linear least-squares formulation provides a principled way to actively enforce a $\textit{well-conditioned}$ parameter space for meta-learning models based on the concepts of the condition number and local curvature. Our comprehensive evaluations show that the proposed method significantly outperforms its unconstrained counterpart especially during initial a…
The capacity of meta-learning algorithms to quickly adapt to a variety of tasks, including ones they did not experience during meta-training, has been a key factor in the recent success of these methods on few-shot learning problems. This particular advantage of using meta-learning over standard supervised or reinforcement learning is only well founded under the assumption that the adaptation phase does improve the performance of our model on the task of interest. However, in the classical framework of meta-learning, this constraint is only mildly enforced, if not at all, and we only see an im…
University of California, Davis（加利福尼亚大学戴维斯分校）；Google Inc.（谷歌公司）
Numerous new dialog domains are being created every day while collecting data for these domains is extremely costly since it involves human interactions. Therefore, it is essential to develop algorithms that can adapt to different domains efficiently when building data-driven dialog models. The most recent researches on domain adaption focus on giving the model a better initialization, rather than optimizing the adaptation process. We propose an efficient domain adaptive task-oriented dialog system model, which incorporates a meta-teacher model to emphasize the different impacts between genera…
Meta-learning has been sufficiently validated to be beneficial for low-resource neural machine translation (NMT). However, we find that meta-trained NMT fails to improve the translation performance of the domain unseen at the meta-training stage. In this paper, we aim to alleviate this issue by proposing a novel meta-curriculum learning for domain adaptation in NMT. During meta-training, the NMT first learns the similar curricula from each domain to avoid falling into a bad local optimum early, and finally learns the curricula of individualities to improve the model robustness for learning dom…
Department of Computer Science, University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校计算机科学系）
This paper improves state-of-the-art visual object trackers that use online adaptation. Our core contribution is an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking. The meta learning is driven by the goal of deep networks that can quickly be adapted to robustly model a particular target in future frames. Ideally the resulting models focus on features that are useful for future frames, and avoid overfitting to background clutter, small parts of the target, or noise. By enforcing a small number of update iterations during meta-learn…
University of Oxford（牛津大学）；Latent Logic（潜在逻辑公司）；Microsoft Research（微软研究院）
We propose CAVIA for meta-learning, a simple extension to MAML that is less prone to meta-overfitting, easier to parallelise, and more interpretable. CAVIA partitions the model parameters into two parts: context parameters that serve as additional input to the model and are adapted on individual tasks, and shared parameters that are meta-trained and shared across tasks. At test time, only the context parameters are updated, leading to a low-dimensional task representation. We show empirically that CAVIA outperforms MAML for regression, classification, and reinforcement learning. Our experiment…
Sun Yat-sen University（中山大学）；DarkMatter AI Research（暗物质人工智能研究院）
(Unsupervised) Domain Adaptation (DA) seeks for classifying target instances when solely provided with source labeled and target unlabeled examples for training. Learning domain-invariant features helps to achieve this goal, whereas it underpins unlabeled samples drawn from a single or multiple explicit target domains (Multi-target DA). In this paper, we consider a more realistic transfer scenario: our target domain is comprised of multiple sub-targets implicitly blended with each other, so that learners could not identify which sub-target each unlabeled sample belongs to. This Blending-target…
Samsung AI Center Cambridge（三星人工智能中心剑桥）；The University of Edinburgh（爱丁堡大学）
Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to address this problem through different ways to minimise the domain shift between source and target datasets. In this paper we take an orthogonal perspective and propose a framework to further enhance performance by meta-learning the initial conditions of existing DA algorithms. This is challenging compared to the more widely considered setting of few-shot meta…
Recently, large, high-quality public datasets have led to the development of convolutional neural networks that can detect lymph node metastases of breast cancer at the level of expert pathologists. Many cancers, regardless of the site of origin, can metastasize to lymph nodes. However, collecting and annotating high-volume, high-quality datasets for every cancer type is challenging. In this paper we investigate how to leverage existing high-quality datasets most efficiently in multi-task settings for closely related tasks. Specifically, we will explore different training and domain adaptation…
Humans and animals can learn complex predictive models that allow them to accurately and reliably reason about real-world phenomena, and they can adapt such models extremely quickly in the face of unexpected changes. Deep neural network models allow us to represent very complex functions, but lack this capacity for rapid online adaptation. The goal in this paper is to develop a method for continual online learning from an incoming stream of data, using deep neural network models. We formulate an online learning procedure that uses stochastic gradient descent to update model parameters, and an …
Delft University of Technology（代尔夫特理工大学）；University Libre du Bruxelles（布鲁塞尔自由大学）；Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所IPA）
Self-adaptation can be used in robotics to increase system robustness and reliability. This work describes the Metacontrol method for self-adaptation in robotics. Particularly, it details how the MROS (Metacontrol for ROS Systems) framework implements and packages Metacontrol, and it demonstrate how MROS can be applied in a navigation scenario where a mobile robot navigates in a factory floor. Video: https://www.youtube.com/watch?v=ISe9aMskJuE
Colorado School of Mines（科罗拉多矿业学院）；Army Research Laboratory (ARL)（美国陆军研究实验室（ARL））
Ground robots require the crucial capability of traversing unstructured and unprepared terrains and avoiding obstacles to complete tasks in real-world robotics applications such as disaster response. When a robot operates in off-road field environments such as forests, the robot's actual behaviors often do not match its expected or planned behaviors, due to changes in the characteristics of terrains and the robot itself. Therefore, the capability of robot adaptation for consistent behavior generation is essential for maneuverability on unstructured off-road terrains. In order to address the ch…
Spiking Neural Networks (SNNs) have recently gained popularity as machine learning models for on-device edge intelligence for applications such as mobile healthcare management and natural language processing due to their low power profile. In such highly personalized use cases, it is important for the model to be able to adapt to the unique features of an individual with only a minimal amount of training data. Meta-learning has been proposed as a way to train models that are geared towards quick adaptation to new tasks. The few existing meta-learning solutions for SNNs operate offline and requ…
Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal Embeddings
Department of Computer Science, Aalto University, Espoo, Finland（Aalto大学计算机科学系）；ELLIS Institute Finland, Espoo, Finland（芬兰ELLIS研究所）；Department of Computer Science, University of Manchester, United Kingdom（曼彻斯特大学计算机科学系）
A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm
College of Science, National University of Defense Technology（国防科技大学理学院）；College of Systems Engineering, National University of Defense Technology（国防科技大学系统工程学院）
Few-shot meta-learning methods consider the problem of learning new tasks from a small, fixed number of examples, by meta-learning across static data from a set of previous tasks. However, in many real world settings, it is more natural to view the problem as one of minimizing the total amount of supervision --- both the number of examples needed to learn a new task and the amount of data needed for meta-learning. Such a formulation can be studied in a sequential learning setting, where tasks are presented in sequence. When studying meta-learning in this online setting, a critical question ari…
Towards Foundation Model for Chemical Reactor Modeling: Meta-Learning with Physics-Informed Adaptation
Department of Chemical and Biomolecular Engineering, National University of Singapore（化学与生物分子工程系，新加坡国立大学）；Artificial Intelligence Institute, National University of Singapore（人工智能研究所，新加坡国立大学）
Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns from different visual domains, it tends to forget the past domains in favor of the most recent ones. In this context, we show that one way to learn models that are inherently more robust against forgetting is domain randomization - for vision tasks, randomizing the current domain's distribution with heavy image manipulations. Building on this result, we devi…
How can deep learning systems flexibly reuse their knowledge? Toward this goal, we propose a new class of challenges, and a class of architectures that can solve them. The challenges are meta-mappings, which involve systematically transforming task behaviors to adapt to new tasks zero-shot. The key to achieving these challenges is representing the task being performed in such a way that this task representation is itself transformable. We therefore draw inspiration from functional programming and recent work in meta-learning to propose a class of Homoiconic Meta-Mapping (HoMM) approaches that …
Speaker adaptive training (SAT) of neural network acoustic models learns models in a way that makes them more suitable for adaptation to test conditions. Conventionally, model-based speaker adaptive training is performed by having a set of speaker dependent parameters that are jointly optimised with speaker independent parameters in order to remove speaker variation. However, this does not scale well if all neural network weights are to be adapted to the speaker. In this paper we formulate speaker adaptive training as a meta-learning task, in which an adaptation process using gradient descent …
Colorado School of Mines（科罗拉多矿业学院）；US Army Research Laboratory（美国陆军研究实验室）
Terrain adaptation is an essential capability for a ground robot to effectively traverse unstructured off-road terrain in real-world field environments such as forests. However, the expected robot behaviors generated by terrain adaptation methods cannot always be executed accurately due to setbacks such as wheel slip and reduced tire pressure. To address this problem, we propose a novel approach for consistent behavior generation that enables the ground robot's actual behaviors to more accurately match expected behaviors while adapting to a variety of unstructured off-road terrain. Our approac…
UC San Diego（加州大学圣迭戈分校）；HKUST Robotics Institute（香港科技大学机器人研究所）；University of Bristol（布里斯托大学）
Manual visual inspection performed by certified inspectors is still the main form of road pothole detection. This process is, however, not only tedious, time-consuming and costly, but also dangerous for the inspectors. Furthermore, the road pothole detection results are always subjective, because they depend entirely on the individual experience. Our recently introduced disparity (or inverse depth) transformation algorithm allows better discrimination between damaged and undamaged road areas, and it can be easily deployed to any semantic segmentation network for better road pothole detection r…
Colorado School of Mines（科罗拉多矿业学院）；DEVCOM Army Research Laboratory（DEVCOM陆军研究实验室）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
When robots operate in real-world off-road environments with unstructured terrains, the ability to adapt their navigational policy is critical for effective and safe navigation. However, off-road terrains introduce several challenges to robot navigation, including dynamic obstacles and terrain uncertainty, leading to inefficient traversal or navigation failures. To address these challenges, we introduce a novel approach for adaptation by negotiation that enables a ground robot to adjust its navigational behaviors through a negotiation process. Our approach first learns prediction models for va…
Uppsala University（乌普萨拉大学）；KTH Royal Institute of Technology（KTH皇家理工学院）
In socially assistive robotics, an important research area is the development of adaptation techniques and their effect on human-robot interaction. We present a meta-learning based policy gradient method for addressing the problem of adaptation in human-robot interaction and also investigate its role as a mechanism for trust modelling. By building an escape room scenario in mixed reality with a robot, we test our hypothesis that bi-directional trust can be influenced by different adaptation algorithms. We found that our proposed model increased the perceived trustworthiness of the robot and in…
Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments. Recent work learns risk measures which measure the probability of violating constraints, which can then be used to enable safety. However, learning such risk measures requires significant interaction with the environment, resulting in excessive constraint violations during learning. Furthermore, these measures are not easily transferable to new environments. We cast safe exploration as an offline meta-RL problem, where the objective is to leverage examples of safe and unsafe behavior across a ran…
Aalto University（阿尔托大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）
Modern reinforcement learning methods suffer from low sample efficiency and unsafe exploration, making it infeasible to train robotic policies entirely on real hardware. In this work, we propose to address the problem of sim-to-real domain transfer by using meta learning to train a policy that can adapt to a variety of dynamic conditions, and using a task-specific trajectory generation model to provide an action space that facilitates quick exploration. We evaluate the method by performing domain adaptation in simulation and analyzing the structure of the latent space during adaptation. We the…
