Advantage of prediction and mental imagery for goal‐directed behaviour in agents and robots

Krichmar, Jeffrey L.; Hwu, Tiffany; Zou, Xinyun; Hylton, Todd

doi:10.1049/ccs.2018.0002

Cited by 7 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once the environment map has been constructed, the robot can use a path planning algorithm, such as A * [17] or RRT * [18], to generate a collision-free trajectory to reach the target location, even if there are obstacles [19,20]. With the development of deep learning, some work [21,22,23] built detailed semantic maps from images for complex indoor navigation learning in simulator [24,25,26].…”

Section: Related Workmentioning

confidence: 99%

Long-term object search using incremental scene graph updating

et al. 2022

View full text Add to dashboard Cite

Effective searching for target objects in indoor scenes is essential for household robots to perform daily tasks. With the establishment of a precise map, the robot can navigate to a fixed static target. However, it is difficult for mobile robots to find movable objects like cups. To address this problem, we establish an object search framework that combines navigation map, semantic map, and scene graph. The robot updates the scene graph to achieve a long-term target search. Considering the different start positions of the robots, we weigh the distance the robot walks and the probability of finding objects to achieve global path planning. The robot can continuously update the scene graph in a dynamic environment to memorize the position relation of objects in the scene. This method has been realized in both simulation and real-world environments. The experimental results show the feasibility and effectiveness of this method.

show abstract

Section: Related Workmentioning

confidence: 99%

Long-term object search using incremental scene graph updating

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Therefore, biologically-inspired models of locomotion would allow robots to develop better sensorimotor skills and accomplish complex tasks (e.g., delivery, predator-prey, search, and rescue, etc.) in the real world (Zabala et al, 2012;Nelson et al, 2018;Krichmar et al, 2019). Because their actions are repeatable and their control systems are reprogrammable and durable, neurorobots can be reverse-engineered to better understand the actual interactions among an animal's body, control mechanism, and living environment (Ijspeert, 2008(Ijspeert, , 2014Goulding, 2009;Kiehn, 2016).…”

Section: Locomotionmentioning

confidence: 99%

Neurorobots as a Means Toward Neuroethology and Explainable AI

et al. 2020

Self Cite

View full text Add to dashboard Cite

Understanding why deep neural networks and machine learning algorithms act as they do is a difficult endeavor. Neuroscientists are faced with similar problems. One way biologists address this issue is by closely observing behavior while recording neurons or manipulating brain circuits. This has been called neuroethology. In a similar way, neurorobotics can be used to explain how neural network activity leads to behavior. In real world settings, neurorobots have been shown to perform behaviors analogous to animals. Moreover, a neuroroboticist has total control over the network, and by analyzing different neural groups or studying the effect of network perturbations (e.g., simulated lesions), they may be able to explain how the robot's behavior arises from artificial brain activity. In this paper, we review neurorobot experiments by focusing on how the robot's behavior leads to a qualitative and quantitative explanation of neural activity, and vice versa, that is, how neural activity leads to behavior. We suggest that using neurorobots as a form of computational neuroethology can be a powerful methodology for understanding neuroscience, as well as for artificial intelligence and machine learning.

show abstract

“…If one wants to extract parameters required for robotic execution, such as locations of objects to be grasped or target locations of where to put the objects, one has to post-process the mental images showing scenes before the action and after the action. In addition, we do not include actions of other agents in our mental models (as in Krichmar et al, 2019 ).…”

Section: Introductionmentioning

confidence: 99%

Simulated mental imagery for robotic task planning

Li,

Kulvicius,

Tamosiunaite

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

Traditional AI-planning methods for task planning in robotics require a symbolically encoded domain description. While powerful in well-defined scenarios, as well as human-interpretable, setting this up requires a substantial effort. Different from this, most everyday planning tasks are solved by humans intuitively, using mental imagery of the different planning steps. Here, we suggest that the same approach can be used for robots too, in cases which require only limited execution accuracy. In the current study, we propose a novel sub-symbolic method called Simulated Mental Imagery for Planning (SiMIP), which consists of perception, simulated action, success checking, and re-planning performed on 'imagined' images. We show that it is possible to implement mental imagery-based planning in an algorithmically sound way by combining regular convolutional neural networks and generative adversarial networks. With this method, the robot acquires the capability to use the initially existing scene to generate action plans without symbolic domain descriptions, while at the same time, plans remain human-interpretable, different from deep reinforcement learning, which is an alternative sub-symbolic approach. We create a data set from real scenes for a packing problem of having to correctly place different objects into different target slots. This way efficiency and success rate of this algorithm could be quantified.

show abstract

Advantage of prediction and mental imagery for goal‐directed behaviour in agents and robots

Cited by 7 publications

References 37 publications

Long-term object search using incremental scene graph updating

Long-term object search using incremental scene graph updating

Neurorobots as a Means Toward Neuroethology and Explainable AI

Simulated mental imagery for robotic task planning

Contact Info

Product

Resources

About