Academia.edu no longer supports Internet Explorer.
To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to upgrade your browser.
2019, International Conference on Humanoid Robots (Humanoids)
Social robots should be able to operate in highly challenging environments populated with complex objects and in social settings involving humans, animals, and other robots. Despite these challenges, we expect these robots to be mindful of us while executing their tasks, demonstrating adaptive behaviors. Conventional machine learning approaches do not scale well with the dynamic nature of such real-world interactions as they require samples from stationary data distributions. The real-world is not stationary, it changes continuously. In such contexts, training data and learning objectives may also change rapidly. Lifelong learning is able to address this problem by learning incrementally and facilitating the learning of new concepts, situations, and abilities. Consider a robot that is vacuuming while a person is reading a newspaper. When given negative feedback in this situation, the robot should be able to identify this as a new context, and thereon adapt its behaviors accordingly in similar spatial or social contexts - e.g., when people are watching TV, the robot should be able to link this situation to the previously experienced one and avoid vacuuming.
Journal of Physical Agents (JoPha), 2012
Frontiers in Neurorobotics, 2021
Long-term human-robot interaction requires the continuous acquisition of knowledge. This ability is referred to as lifelong learning (LL). LL is a long-standing challenge in machine learning due to catastrophic forgetting, which states that continuously learning from novel experiences leads to a decrease in the performance of previously acquired knowledge. Two recently published LL approaches are the Growing Dual-Memory (GDM) and the Self-organizing Incremental Neural Network+ (SOINN+). Both are growing neural networks that create new neurons in response to novel sensory experiences. The latter approach shows state-of-the-art clustering performance on sequentially available data with low memory requirements regarding the number of nodes. However, classification capabilities are not investigated. Two novel contributions are made in our research paper: (I) An extended SOINN+ approach, called associative SOINN+ (A-SOINN+), is proposed. It adopts two main properties of the GDM model to facilitate classification. (II) A new LL object recognition dataset (v-NICO-World-LL) is presented. It is recorded in a nearly photorealistic virtual environment, where a virtual humanoid robot manipulates 100 different objects belonging to 10 classes. Real-world and artificially created background images, grouped into four different complexity levels, are utilized. The A-SOINN+ reaches similar state-of-the-art classification accuracy results as the best GDM architecture of this work and consists of 30 to 350 times fewer neurons, evaluated on two LL object recognition datasets, the novel v-NICO-World-LL and the well-known CORe50. Furthermore, we observe an approximately 268 times lower training time. These reduced numbers result in lower memory and computational requirements, indicating higher suitability for autonomous social robots with low computational resources to facilitate a more efficient LL during long-term human-robot interactions.
Adaptation is a critical component of collaboration. Nevertheless, online learning is not yet used in most successful human-robot interactions, especially when the human’s and robot’s goals are not fully aligned. There are at least two barriers to the successful application of online learning in HRI. First, typical machine learning algorithms do not learn at time scales that support effective interactions with people. Algorithms that learn at sufficiently fast time scales often produce myopic strategies that do not lead to good long-term collaborations. Second, random exploration, a core component of most online-learning algorithms, can be problematic for developing collaborative relationships with a human partner. We anticipate that a new genre of online-learning algorithms can overcome these two barriers when paired with (cheap-talk) communication. In this paper, we overview our efforts in these two areas to produce a situation-independent, learning system that quickly learns to collaborate with a human partner.
Journal of Intelligent & Robotic Systems
Service robots are appearing more and more in our daily life. The development of service robots combines multiple fields of research, from object perception to object manipulation. The state-of-the-art continues to improve to make a proper coupling between object perception and manipulation. This coupling is necessary for service robots not only to perform various tasks in a reasonable amount of time but also to continually adapt to new environments and safely interact with non-expert human users. Nowadays, robots are able to recognize various objects, and quickly plan a collision-free trajectory to grasp a target object in predefined settings. Besides, in most of the cases, there is a reliance on large amounts of training data. Therefore, the knowledge of such robots is fixed after the training phase, and any changes in the environment require complicated, time-consuming, and expensive robot re-programming by human experts. Therefore, these approaches are still too rigid for real-l...
arXiv (Cornell University), 2023
Oralia, 2024
La pregunta de este trabajo es: ¿hay una variación en la capacidad de argumentar en función de la procedencia geográfica? Para responderla, se analiza la argumentatividad de hablantes de una misma lengua. Por argumentatividad entendemos aquí la disposición a dar razones. Esta disposición será analizada en dos comunidades de inmigrantes (peruanos y venezolanos) en el Chile contemporáneo, que residen en las dos regiones principales del país. Hemos utilizado hablantes chilenos como grupo de control. El objetivo principal del trabajo fue determinar descriptivamente si acaso hay diferencias en argumentatividad entre estas tres comunidades de hablantes. Se utilizaron las respuestas orales a una entrevista estructurada. Entre los hallazgos principales destaca que: 1) los hablantes inmigrantes procedentes de Perú articulan mejor sus puntos de vista, vale decir, son capaces de generar una aserción que representa sus creencias apoyadas con razones, 2) el nivel educacional es una variable determinante, y 3) la variable género, independiente de nacionalidad, no genera ninguna diferencia relevante.
Scripture:Canon::Text:Context: Essays Honoring Lewis Lancaster, 1999
dionesius budi, 2016
Journal of the Academy of Marketing Science, 2013
ACROSS THE MEDITERRANEAN – ALONG THE NILE Studies in Egyptology, Nubiology and Late Antiquity Dedicated to László Török on the Occasion of His 75th Birthday Volume 1, 2018
Ecology and Evolution, 2018
Polymer International
Biomedical research, 2011
British Journal of Surgery, 2021
Revista Ciencia Em Extensao, 2011
The Journal of Epic Literature, 2022
The 1st International Electronic Conference on Applied Sciences, 2020
Journal für Mobilität und Verkehr, 2024