Goal-oriented robot navigation learning using a multi-scale space representation

Llofriu, Martín; Tejera, Gonzalo; Contreras, Marta; Pelc, Tatiana; Fellous, Jean-Marc; Weitzenfeld, Alfredo

doi:10.1016/j.neunet.2015.09.006

Cited by 28 publications

(10 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This sensing-and-storage system for navigation is consistent with the intertwining role of the hippocampus in spatial cognition and episodic memory (Burgess et al 2002;Eichenbaum 2000Eichenbaum , 2017bEichenbaum and Cohen 2014;Ekstrom and Ranganath 2017;Howard et al 2005;Knierim 2015;Miller et al 2013;Olton et al 1979). It is also in line with the primary approach used to implement an artificial navigation system (e.g., Llofriu et al 2015;Milford 2008;Milford and Schulz 2014;Thrun 2008).…”

Section: A Positioning System Vs a Navigation Systemsupporting

confidence: 74%

Human spatial representation: what we cannot learn from the studies of rodent navigation

Zhao

2018

Journal of Neurophysiology

View full text Add to dashboard Cite

Studies of human and rodent navigation often reveal a remarkable cross-species similarity between the cognitive and neural mechanisms of navigation. Such cross-species resemblance often overshadows some critical differences between how humans and nonhuman animals navigate. In this review, I first argued that a navigation system requires both a storage system (i.e., representing spatial information) and a positioning system (i.e., sensing spatial information) to operate. I then argued that the way humans represent spatial information is different from that inferred from the cellular activity observed during rodent navigation. Such difference spans the whole hierarchy of spatial representation, from representing the structure of environment to the representation of sub-regions of an environment, routes and paths, and the distance and direction relative to a goal location. These cross-species inconsistencies suggested that what we learned from rodent navigation does not always transferable to human navigation. Finally, I argue for closing the loop for the dominant, unidirectional animal-to-human approach in navigation research, so that insights from behavioral studies of human navigation may also flow back to shed light on the cellular mechanisms of navigation for both humans and other mammals (i.e., a human-to-animal approach).

show abstract

Section: A Positioning System Vs a Navigation Systemsupporting

confidence: 74%

Human spatial representation: what we cannot learn from the studies of rodent navigation

Zhao

2018

Journal of Neurophysiology

View full text Add to dashboard Cite

show abstract

“…Although little is known about how the extended hippocampal system supports spatial rep- [32,37,166,167], more work in this area is also required.…”

Section: A Multi-scale Memory System For Representing Complex Large-smentioning

confidence: 99%

A Role for the Longitudinal Axis of the Hippocampus in Multiscale Representations of Large and Complex Spatial Environments and Mnemonic Hierarchies

Harland¹,

Contreras²,

Fellous³

2018

The Hippocampus - Plasticity and Functions

View full text Add to dashboard Cite

The hippocampus is involved in spatial navigation and memory in rodents and humans. Anatomically, the hippocampus extends along a longitudinal axis that shows a combination of graded and specific interconnections with neocortical and subcortical brain areas. Functionally, place cells are found all along the longitudinal axis and exhibit gradients of properties including an increasing dorsal-to-ventral place field size. We propose a view of hippocampal function in which fine-dorsal to coarse-ventral overlapping representations collaborate to form a multi-level representation of spatial and episodic memory that is dominant during navigation in large and complex environments or when encoding complex memories. This view is supported by the fact that the effects of ventral hippocampal damage are generally only found in larger laboratoryscale environments, and by the finding that human virtual navigation studies associate ventral hippocampal involvement with increased environmental complexity. Other mechanisms such as the ability of place cells to exhibit multiple fields and their ability to scale their fields with changes in environment size may be utilized when forming large-scale cognitive maps. Coarse-grained ventral representations may overlap with and provide multi-modal global contexts to finer-grained intermediate and dorsal representations, a mechanism that may support mnemonic hierarchies of autobiographical memory in humans.

show abstract

“…Numerous researchers have used the Morris water maze experiment [35][36][37][38], in which a rat must find a hidden platform in its environment. This has become the standard paradigm for measuring navigation tasks.…”

Section: Simulation Setupmentioning

confidence: 99%

A Brain-Inspired Goal-Oriented Robot Navigation System

2019

Applied Sciences

View full text Add to dashboard Cite

Autonomous navigation in unknown environments is still a challenge for robotics. Many efforts have been exerted to develop truly autonomous goal-oriented robot navigation models based on the neural mechanism of spatial cognition and mapping in animals’ brains. Inspired by the Semantic Pointer Architecture Unified Network (SPAUN) neural model and neural navigation mechanism, we developed a brain-like biologically plausible mathematical model and applied it to robotic spatial navigation tasks. The proposed cognitive navigation framework adopts a one-dimensional ring attractor to model the head-direction cells, uses the sinusoidal interference model to obtain the grid-like activity pattern, and gets optimal movement direction based on the entire set of activities. The application of adaptive resonance theory (ART) could effectively reduce resource consumption and solve the problem of stability and plasticity in the dynamic adjustment network. This brain-like system model broadens the perspective to develop more powerful autonomous robotic navigation systems. The proposed model was tested under different conditions and exhibited superior navigation performance, proving its effectiveness and reliability.

show abstract

Goal-oriented robot navigation learning using a multi-scale space representation

Cited by 28 publications

References 55 publications

Human spatial representation: what we cannot learn from the studies of rodent navigation

Human spatial representation: what we cannot learn from the studies of rodent navigation

A Role for the Longitudinal Axis of the Hippocampus in Multiscale Representations of Large and Complex Spatial Environments and Mnemonic Hierarchies

A Brain-Inspired Goal-Oriented Robot Navigation System

Contact Info

Product

Resources

About