Related papers: Multi-Objective Algorithms for Learning Open-Ended…
Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single…
Machine learning problems with multiple objective functions appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in…
Controlled execution of dynamic motions in quadrupedal robots, especially those with articulated soft bodies, presents a unique set of challenges that traditional methods struggle to address efficiently. In this study, we tackle these…
In the field of autonomous Unmanned Aerial Vehicles (UAVs) landing, conventional approaches fall short in delivering not only the required precision but also the resilience against environmental disturbances. Yet, learning-based algorithms…
We show dynamic locomotion strategies for wheeled quadrupedal robots, which combine the advantages of both walking and driving. The developed optimization framework tightly integrates the additional degrees of freedom introduced by the…
Machine learning (ML) methods offer a wide range of configurable hyperparameters that have a significant influence on their performance. While accuracy is a commonly used performance objective, in many settings, it is not sufficient.…
We present ZSL-RPPO, an improved zero-shot learning architecture that overcomes the limitations of teacher-student neural networks and enables generating robust, reliable, and versatile locomotion for quadrupedal robots in challenging…
Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic…
Human drivers exhibit individual preferences regarding driving style. Adapting autonomous vehicles to these preferences is essential for user trust and satisfaction. However, existing end-to-end driving approaches often rely on predefined…
The development of Multimodal Large Language Models (MLLMs) has seen significant advancements with increasing demands in various fields (e.g., multimodal agents, embodied intelligence). While model-driven approaches attempt to enhance MLLMs…
Multi-Objective Reinforcement Learning (MORL) is a generalization of traditional Reinforcement Learning (RL) that aims to optimize multiple, often conflicting objectives simultaneously rather than focusing on a single reward. This approach…
Recent advances in the visualization of continuous multimodal multi-objective optimization (MMMOO) landscapes brought a new perspective to their search dynamics. Locally efficient (LE) sets, often considered as traps for local search, are…
This paper proposes an inverse optimal control method which enables a robot to incrementally learn a control objective function from a collection of trajectory segments. By saying incrementally, it means that the collection of trajectory…
To avoid myopic behavior, multi-step lookahead Bayesian optimization (BO) algorithms consider the sequential nature of BO and have demonstrated promising results in recent years. However, owing to the curse of dimensionality, most of these…
Wheeled-legged robots have the potential for highly agile and versatile locomotion. The combination of legs and wheels might be a solution for any real-world application requiring rapid, and long-distance mobility skills on challenging…
In recent years, multi-objective optimization (MOO) emerges as a foundational problem underpinning many multi-agent multi-task learning applications. However, existing algorithms in MOO literature remain limited to centralized learning…
Quadrupedal robots have played a crucial role in various environments, from structured environments to complex harsh terrains, thanks to their agile locomotion ability. However, these robots can easily lose their locomotion functionality if…
With the research into development of quadruped robots picking up pace, learning based techniques are being explored for developing locomotion controllers for such robots. A key problem is to generate leg trajectories for continuously…
Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence due to catastrophic forgetting. Large language models (LLMs) are often impractical to frequent…
Performing agile navigation with four-legged robots is a challenging task due to the highly dynamic motions, contacts with various parts of the robot, and the limited field of view of the perception sensors. In this paper, we propose a…