相关论文: Simplex-enabled Safe Continual Learning Machine

Imitation Learning has provided a promising approach to learning complex robot behaviors from expert demonstrations. However, learned policies can make errors that lead to safety violations, which limits their deployment in safety-critical…

Autonomous driving promises significant advancements in mobility, road safety and traffic efficiency, yet reinforcement learning and imitation learning face safe-exploration and distribution-shift challenges. Although human-AI collaboration…

Continual Learning is an important and challenging problem in machine learning, where models must adapt to a continuous stream of new data without forgetting previously acquired knowledge. While existing frameworks are built on PyTorch, the…

Autonomous driving vehicles with self-learning capabilities are expected to evolve in complex environments to improve their ability to cope with different scenarios. However, most self-learning algorithms suffer from low learning efficiency…

With the growing popularity of deep reinforcement learning (DRL), human-in-the-loop (HITL) approach has the potential to revolutionize the way we approach decision-making problems and create new opportunities for human-AI collaboration. In…

Federated Learning (FL) is an emerging machine learning paradigm that enables multiple clients to jointly train a model to take benefits from diverse datasets from the clients without sharing their local training datasets. FL helps reduce…

Transformer based models are increasingly being used in various domains including recommender systems (RS). Pretrained transformer models such as BERT have shown good performance at language modelling. With the greater ability to model…

Despite recent remarkable achievements in quadruped control, it remains challenging to ensure robust and compliant locomotion in the presence of unforeseen external disturbances. Existing methods prioritize locomotion robustness over…

A Learning Model Predictive Controller (LMPC) for linear system in presented. The proposed controller is an extension of the LMPC [1] and it aims to decrease the computational burden. The control scheme is reference-free and is able to…

This article introduces a novel sample-efficient curriculum learning (CL) approach for training an end-to-end reinforcement learning (RL) policy for robust stabilization of a Quadrotor. The learning objective is to simultaneously stabilize…

Continual Reinforcement Learning (CRL) aims to develop lifelong learning agents to continuously acquire knowledge across diverse tasks while mitigating catastrophic forgetting. This requires efficiently managing the stability-plasticity…

Long-horizon robotic manipulation tasks require executing multiple interdependent subtasks in strict sequence, where errors in detecting subtask completion can cascade into downstream failures. Existing Vision-Language-Action (VLA) models…

Motivated by recent advances in Deep Learning for robot control, this paper considers two learning algorithms in terms of how they acquire demonstrations. "Human-Centric" (HC) sampling is the standard supervised learning algorithm, where a…

Learning reliably safe autonomous control is one of the core problems in trustworthy autonomy. However, training a controller that can be formally verified to be safe remains a major challenge. We introduce a novel approach for learning…

Safe reinforcement learning (SafeRL) extends standard reinforcement learning with the idea of safety, where safety is typically defined through the constraint of the expected cost return of a trajectory being below a set limit. However,…

This work explores the feasibility of specialized hardware implementing the Cortical Learning Algorithm (CLA) in order to fully exploit its inherent advantages. This algorithm, which is inspired in the current understanding of the mammalian…

Safe reinforcement learning (Safe RL) aims to ensure policy performance while satisfying safety constraints. However, most existing Safe RL methods assume benign environments, making them vulnerable to adversarial perturbations commonly…

Data-driven methods have become paramount in modern systems and control problems characterized by growing levels of complexity. In safety-critical environments, deploying these methods requires rigorous guarantees, a need that has motivated…

We consider the safe reinforcement learning (RL) problem of maximizing utility with extremely low constraint violation rates. Assuming no prior knowledge or pre-training of the environment safety model given a task, an agent has to learn,…

Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise, and unstructured contact conditions. We introduce SafeMind, a differentiable stochastic…