User profiles for Yoshihiro Ohama
Yoshihiro OhamaVerified email at mosk.tytlabs.co.jp Cited by 360 |
Ego-motion estimation and moving object tracking using multi-layer lidar
T Miyasaka, Y Ohama… - 2009 IEEE intelligent …, 2009 - ieeexplore.ieee.org
This paper presents an approach for the robust recognition of a complex and dynamic driving
environment, such as an urban area, using on-vehicle multilayer LIDAR. The multilayer …
environment, such as an urban area, using on-vehicle multilayer LIDAR. The multilayer …
Improvements in Perpendicular Reverse Parking by Directing Drivers' Preliminary Behavior
Driving vehicles requires mastery of a multitude of tasks. Among these, parking is one task
that most drivers feel they are not as skilled as they would like to be. In this paper, we focus on …
that most drivers feel they are not as skilled as they would like to be. In this paper, we focus on …
Toward a practical wall see-through system for drivers: How simple can it be?
This study specifically examines wall see-through visualization for drivers at blind corners to
prevent crossing collisions. We believe that realizing the desired effect with the simplest …
prevent crossing collisions. We believe that realizing the desired effect with the simplest …
A parallel forward-backward propagation learning scheme for auto-encoders
Y Ohama, T Yoshimura - … , ICONIP 2017, Guangzhou, China, November 14 …, 2017 - Springer
Auto-encoders constitute one popular deep learning architecture for feature extraction. Since
an auto-encoder has at least one bottle neck layer for feature representation and at least …
an auto-encoder has at least one bottle neck layer for feature representation and at least …
A simplified forward-propagation learning rule applied to adaptive closed-loop control
Y Ohama, N Fukumura, Y Uno - International Conference on Artificial …, 2005 - Springer
In terms of computational neuroscience, several theoretical learning schemes have been
proposed to acquire suitable motor controllers in the human brain. The controllers have been …
proposed to acquire suitable motor controllers in the human brain. The controllers have been …
[PDF][PDF] A computational framework for estimating collision risk against pedestrians
T Shimizu, Y Ohama, S Nagata… - R&D Review of Toyota …, 2012 - tytlabs.co.jp
Recently, preventive safety systems such as Forward Collision Warning (FCW)(1) and
Autonomous Emergency Braking (AEB)(2) have been made commercially available. Their …
Autonomous Emergency Braking (AEB)(2) have been made commercially available. Their …
A forward‐propagation learning rule for neural inverse models using a method of recursive least squares
Y Ohama, N Fukumura, Y Uno - Systems and Computers in …, 2005 - Wiley Online Library
A forward‐propagation learning scheme has been proposed to acquire inverse models of
controlled objects in multilayered neural networks. This scheme is quite different from back‐…
controlled objects in multilayered neural networks. This scheme is quite different from back‐…
A forward-propagation rule for acquiring neural inverse models using a RLS algorithm
Y Ohama, N Fukumura, Y Uno - … 2004, Calcutta, India, November 22-25 …, 2004 - Springer
It has been suggested that inverse models serve feedforward controllers in the human brain.
We have proposed a novel learning scheme to acquire a neural inverse model of a …
We have proposed a novel learning scheme to acquire a neural inverse model of a …
MARPF: Multi-Agent and Multi-Rack Path Finding
In environments where many automated guided vehicles (AGVs) operate, planning efficient,
collision-free paths is essential. Related research has mainly focused on environments with …
collision-free paths is essential. Related research has mainly focused on environments with …
Learning of real robot's inverse dynamics by a forward‐propagation learning rule
A forward‐propagation learning rule (FPL) has been proposed for a neural network (NN) to
learn an inverse model of a controlled object. A feature of FPL is that the trajectory error …
learn an inverse model of a controlled object. A feature of FPL is that the trajectory error …