Show Tag: robotics

Select Other Tags

Adams et al. argue that, since the brain is fast and requires little energy, researching biomimetic solutions can help solve the problems that robots have limited energy resources and computing power.

Although Adams et al. argue that biomimetic approaches to robotics promise less energy consumption and processing requirements, they implicitly acknowledge that using spiking neural networks will increase these requirements and is only feasible, if at all, because of recent developments in software and hardware.

Braitenberg postulates the "the law of uphill analysis and downhill invention", which states that it is easier to build something and see what it does (what it can do) than to analyse something just from the observable output.

Neurorobotics is an activity which creates embodied cognitive agents.

Biorobotics has been a driving force in embodiment theory.

The Kalman filter is a good method in many (robotic) multisensory integration problems in dynamic domains.

At the most general level, multisensory integration (or multisensor data fusion) in application contexts is best described in terms of Bayesian theory, its specializations, and approximations to it.

There have been biomimetic solutions to problems in materials sciences, mechanical sciences, sensor technology, and various problems in robotics.

There have been biomimetic solutions to various problems in robotics.

The concept of reduction of the dimensionality of motor space by using motor synergies has been used in robotics.

Biomimetic (neural) robotics can provide feedback to neuroscience.

Jasso and Triesch presented a simulated virtual reality environment for training robotic models.

Jasso and Triesch acknowledge that a simulation does not always follow exactly the laws of physics. In fact, their environment does not simulate any physics except those of human motion.

Jasso and Triesch argue that for the high-level cognition they train, lacking simulations of physics aren't a problem.

Jasso and Triesch argue that their simulated robots are not limited by the capabilities of today's robotic technology.

Active perception and its synonyms usually refer to a sensor which can be moved to change the way it perceives the world.

The way in which the perception of the world changes when the sensor is moved physically is a source of information in addition to static perception of the world.

Kleesiek et al. use a recurrent neural network with parametric bias (RNNPB) to classify objects from the multisensory percepts induced by interacting with them.

A new(ish) approach to AI and robotics is to program agents which are not modularized according to levels of hierarchy or along the perception-action axis, but according to behaviors.

Every module realizes some part of the overall behavior, including some of the necessary perception, processing, and action.

Some part of the architecture then decides which module gets control over which part of the agent at what time.

Simulations can lead researchers to postulate unrealistically reliable sensor data or actuation.

Noise in real experiments can make dynamics more stable.

Embodied robots bring together the complexity of sensing and action the real world poses. These are not present in simple models and simulations.

Biorobotics has been used successfully to study and sometimes validate theoretical biological claims.

Testing biological hypotheses using robots is called `biorobotics'.

Using a material model instead of the actual object of study is useful in two cases:

  • that physical model is better understood,
  • it is easier to use the model than the original.

Biorobotics is a case of using a material model to understand biological organisms for both reasons given by Rosenblueth and Wiener:

  • robots are generally better understood than the real thing (because we construct them)
  • they are easier studied for technical and for ethical reasons.

Through simulations of neurons (and neuron ensembles), numbers of neurons can be monitored over time scales which both are not possible in vivo.

This is mainly an argument in favor of computational neuroscience. It is not so valid for ANN in classical AI where neuronal models are quite detached from biological neurons.

According to Rucci et al., neuroscientists can use robots to quantitatively test and analyze their theories.

The degree to which neuroscientists can draw conclusions from computational models depends on biological accuracy.

Sensory noise in robotic experiments validates a model's robustness. It is always realistic (but not necessarily natural).