[HTML][HTML] Robot learning from randomized simulations: A review
The rise of deep learning has caused a paradigm shift in robotics research, favoring
methods that require large amounts of data. Unfortunately, it is prohibitively expensive to …
methods that require large amounts of data. Unfortunately, it is prohibitively expensive to …
A review of the literature on fuzzy-logic approaches for collision-free path planning of manipulator robots
In recent years, a large number of manipulator robots have been deployed to replace or
assist humans in many repetitive and dangerous tasks. Yet, these robots have complex …
assist humans in many repetitive and dangerous tasks. Yet, these robots have complex …
Robust deep reinforcement learning against adversarial perturbations on state observations
A deep reinforcement learning (DRL) agent observes its states through observations, which
may contain natural measurement errors or adversarial noises. Since the observations …
may contain natural measurement errors or adversarial noises. Since the observations …
Robust reinforcement learning on state observations with learned optimal adversary
We study the robustness of reinforcement learning (RL) with adversarially perturbed state
observations, which aligns with the setting of many adversarial attacks to deep …
observations, which aligns with the setting of many adversarial attacks to deep …
[图书][B] Evolutionary robotics
Evolutionary Robotics is a method for automatically generating artificial brains and
morphologies of autonomous robots. This approach is useful both for investigating the …
morphologies of autonomous robots. This approach is useful both for investigating the …
Noise and the reality gap: The use of simulation in evolutionary robotics
N Jakobi, P Husbands, I Harvey - … on Artificial Life Granada, Spain, June 4 …, 1995 - Springer
The pitfalls of naive robot simulations have been recognised for areas such as evolutionary
robotics. It has been suggested that carefully validated simulations with a proper treatment of …
robotics. It has been suggested that carefully validated simulations with a proper treatment of …
[图书][B] Bio-inspired artificial intelligence: theories, methods, and technologies
D Floreano, C Mattiussi - 2008 - books.google.com
A comprehensive introduction to new approaches in artificial intelligence and robotics that
are inspired by self-organizing biological processes and structures. New approaches to …
are inspired by self-organizing biological processes and structures. New approaches to …
A dynamical systems perspective on agent-environment interaction
RD Beer - Artificial intelligence, 1995 - Elsevier
Using the language of dynamical systems theory, a general theoretical framework for the
synthesis and analysis of autonomous agents is sketched. In this framework, an agent and …
synthesis and analysis of autonomous agents is sketched. In this framework, an agent and …
Modeling adaptive autonomous agents
P Maes - Artificial life, 1993 - direct.mit.edu
One category of research in Artificial Life is concerned with modeling and building so-called
adaptive autonomous agents, which are systems that inhabit a dynamic, unpredictable …
adaptive autonomous agents, which are systems that inhabit a dynamic, unpredictable …
[图书][B] Catching ourselves in the act: Situated activity, interactive emergence, evolution, and human thought
H Hendriks-Jansen - 1996 - books.google.com
Catching Ourselves in the Act uses situated robotics, ethology, and developmental
psychology to erect a new framework for explaining human behavior. Rejecting the cognitive …
psychology to erect a new framework for explaining human behavior. Rejecting the cognitive …