Memristive device based learning for navigation in robots
Source abstract
Abstract
Biomimetic robots have gained attention recently for various applications ranging from resource hunting to search and rescue operations during disasters. Biological species are known to intuitively learn from the environment, gather and process data, and make appropriate decisions. Such sophisticated computing capabilities in robots are difficult to achieve, especially if done in real-time with ultra-low energy consumption. Here, we present a novel memristive device based learning architecture for robots. Two terminal memristive devices with resistive switching of oxide layer are modeled in a crossbar array to develop a neuromorphic platform that can impart active real-time learning capabilities in a robot. This approach is validated by navigating a robot vehicle in an unknown environment with randomly placed obstacles. Further, the proposed scheme is compared with reinforcement learning based algorithms using local and global knowledge of the environment. The simulation as well as experimental results corroborate the validity and potential of the proposed learning scheme for robots. The results also show that our learning scheme approaches an optimal solution for some environment layouts in robot navigation.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Neural dynamics and brain function · Photoreceptor and optogenetics research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (40)
Show source-provided references
1. Shepherd G M · The Synaptic Organization of the Brain · 2003
2. Koch C · Biophysics of Computation: Information Processing in Single Neurons · 2004
3. 10.1109/JPROC.2014.231395410.1109/JPROC.2014.2313954 ↗
4. 10.1038/scientificamerican0505-5610.1038/scientificamerican0505-56 ↗
5. 10.1109/MSPEC.2006.162850410.1109/MSPEC.2006.1628504 ↗
6. 10.1109/JPROC.2014.230463810.1109/JPROC.2014.2304638 ↗
7. 10.1109/iscas.2010.553697010.1109/iscas.2010.5536970 ↗
8. 10.1126/science.125464210.1126/science.1254642 ↗
9. 10.7551/mitpress/9780262028707.001.000110.7551/mitpress/9780262028707.001.0001 ↗
10. 10.1017/CBO978051181570610.1017/CBO9780511815706 ↗
11. 10.1016/S0893-6080(01)00078-810.1016/S0893-6080(01)00078-8 ↗
12. 10.1113/jphysiol.1952.sp00476410.1113/jphysiol.1952.sp004764 ↗
13. 10.1109/TNN.2003.82044010.1109/TNN.2003.820440 ↗
14. 10.1186/1687-5281-2015-110.1186/1687-5281-2015-1 ↗
15. 10.1109/icm.2010.569614210.1109/icm.2010.5696142 ↗
16. 10.1145/2742060.274375610.1145/2742060.2743756 ↗
17. 10.1109/cdc.2013.676096610.1109/cdc.2013.6760966 ↗
18. 10.1109/TED.2011.214779110.1109/TED.2011.2147791 ↗
19. 10.1038/nmat274810.1038/nmat2748 ↗
20. 10.1109/cicc.2011.605529310.1109/cicc.2011.6055293 ↗
21. 10.1007/s11063-013-9315-810.1007/s11063-013-9315-8 ↗
22. 10.1021/nl904092h10.1021/nl904092h ↗
23. 10.1038/srep0533310.1038/srep05333 ↗
24. 10.1109/nanoarch.2013.662303010.1109/nanoarch.2013.6623030 ↗
25. 10.1038/srep2126810.1038/srep21268 ↗
26. 10.1115/DSCC2016-990310.1115/DSCC2016-9903 ↗
27. 10.1109/naecon.2016.785680510.1109/naecon.2016.7856805 ↗
28. 10.3389/fnins.2011.0002610.3389/fnins.2011.00026 ↗
29. Büel B W · 2011
30. 10.1109/robot.2004.130244610.1109/robot.2004.1302446 ↗
31. 10.1162/106454605327890010.1162/1064546053278900 ↗
32. 10.1109/ijcnn.2010.559652510.1109/ijcnn.2010.5596525 ↗
33. 10.1162/neco.2007.19.6.146810.1162/neco.2007.19.6.1468 ↗
34. Evans R · 2012
35. Hebb D O · 2005
36. Snider G S · Nanotechnology · 2007 · 18
37. 10.1109/nanoarch.2008.458579610.1109/nanoarch.2008.4585796 ↗
38. 10.1146/annurev.neuro.24.1.13910.1146/annurev.neuro.24.1.139 ↗
39. 10.1109/55.98131810.1109/55.981318 ↗
40. 10.1109/TRO.2005.85138210.1109/TRO.2005.851382 ↗