Neurorobotics

Krichmar, Jeff

doi:10.4249/scholarpedia.1365

Cited by 6 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DNF implementation of efficient task learning is consistent with the principles of novel robotic designs in the field of neurorobotics. According to Krichmar (2008), key features of a neurorobotic device are (1) a controller inspired by processing principles of the neural system, and (2) the development of new competences and skills through the interaction with a real-world environment. The architecture of the DNF model reflects converging lines of neurophysiological and computational evidence suggesting the existence of two complementary learning systems in the brain (McClelland et al, 1995;O'Reilly & Norman, 2002).…”

Section: Discussion and Future Workmentioning

confidence: 99%

“…A neurorobotic model may not only serve to develop more effective robots but may also provide an embodied test bed for theories of brain function (Krichmar, 2008). In order to further refine the functional two-stage learning model, we plan in future work to compare model assumptions and specific aspects of its dynamic behavior with findings in human sequence learning studies.…”

Section: Discussion and Future Workmentioning

confidence: 99%

See 1 more Smart Citation

Off-line simulation inspires insight: A neurodynamics approach to efficient robot task learning

et al. 2015

View full text Add to dashboard Cite

There is currently an increasing demand for robots able to acquire the sequential organization of tasks from social learning interactions with ordinary people. Interactive learning-by-demonstration and communication is a promising research topic in current robotics research. However, the efficient acquisition of generalized task representations that allow the robot to adapt to different users and contexts is a major challenge. In this paper, we present a dynamic neural field (DNF) model that is inspired by the hypothesis that the nervous system uses the off-line re-activation of initial memory traces to incrementally incorporate new information into structured knowledge. To achieve this, the model combines fast activation-based learning to robustly represent sequential information from single task demonstrations with slower, weight-based learning during internal simulations to establish longer-term associations between neural populations representing individual subtasks. The efficiency of the learning process is tested in an assembly paradigm in which the humanoid robot ARoS learns to construct a toy vehicle from its parts. User demonstrations with different serial orders together with the correction of initial prediction errors allow the robot to acquire generalized task knowledge about possible serial orders and the longer term dependencies between subgoals in very few social learning interactions. This success is shown in a joint action scenario in which ARoS uses the newly acquired assembly plan to construct the toy together with a human partner.

show abstract

Section: Discussion and Future Workmentioning

confidence: 99%

Section: Discussion and Future Workmentioning

confidence: 99%

Off-line simulation inspires insight: A neurodynamics approach to efficient robot task learning

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Apart from the fact that it takes more time until the results are available, this does not pose any limitations in scenarios where the network input comes from an abstract dataset. However, real-time applications like neurorobotics [36] which integrate the neural simulation in a closed control loop are highly sensitive to the speed of the network dynamics. As demonstrated in Sect.…”

Section: Hierarchical Models Of Learning and Cognitionmentioning

confidence: 99%

Computation by Time

Walter

Röhrbein

Knoll

2015

Neural Process Lett

View full text Add to dashboard Cite

Over the last years, the amount of research performed in the field of spiking neural networks has been growing steadily. Spiking neurons are modeled to approximate the complex dynamic behavior of biological neurons. They communicate via discrete impulses called spikes with the actual information being encoded in the timing of these spikes. As already pointed out by Maass in his paper on the third generation of neural network models, this renders time a central factor for neural computation. In this paper, we investigate at different levels of granularity how absolute time and relative timing enable new ways of biologically inspired neural information processing. At the lowest level of single spiking neurons, we give an overview of coding schemes and learning techniques which rely on precisely timed neural spikes. A high-level perspective is provided in the second part of the paper which focuses on the role of time at the network level. The third aspect of time considered in this work is related to the interfacing of neural networks with real-time systems. In this context, we discuss how the concepts of computation by time can be implemented in computer simulations and on specialized neuromorphic hardware. The contributions of this paper are twofold: first, we show how the exact modeling of time in spiking neural networks serves as an important basis for powerful computation based on neurobiological principles. Second, by presenting a range of diverse learning techniques, we prove the biologically plausible applicability of spiking neural networks to real world problems like pattern recognition and path planning.

show abstract

“…Neural-inspired robots that deploy artificial intelligence (AI) and embodied intelligence (i.e., neuro-robots) need to be explained further. Situated in a natural environment, sensing their environment and acting on it, neuro-robots have control systems based on the principles of nervous systems (Krichmar, 2008). We would assume that robots (and neuro-robots) have become more capable than ever before because the cost of sensors has reduced significantly, and AI algorithms have matured exponentially (Silver et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

When neuro-robots go wrong: A review

Khan

Olds²

2023

Front. Neurorobot.

View full text Add to dashboard Cite

Neuro-robots are a class of autonomous machines that, in their architecture, mimic aspects of the human brain and cognition. As such, they represent unique artifacts created by humans based on human understanding of healthy human brains. European Union’s Convention on Roboethics 2025 states that the design of all robots (including neuro-robots) must include provisions for the complete traceability of the robots’ actions, analogous to an aircraft’s flight data recorder. At the same time, one can anticipate rising instances of neuro-robotic failure, as they operate on imperfect data in real environments, and the underlying AI behind such neuro-robots has yet to achieve explainability. This paper reviews the trajectory of the technology used in neuro-robots and accompanying failures. The failures demand an explanation. While drawing on existing explainable AI research, we argue explainability in AI limits the same in neuro-robots. In order to make robots more explainable, we suggest potential pathways for future research.

show abstract

Neurorobotics

Cited by 6 publications

References 0 publications

Off-line simulation inspires insight: A neurodynamics approach to efficient robot task learning

Off-line simulation inspires insight: A neurodynamics approach to efficient robot task learning

Computation by Time

When neuro-robots go wrong: A review

Contact Info

Product

Resources

About