2017
DOI: 10.1002/rob.21731
|View full text |Cite
|
Sign up to set email alerts
|

Autonomous car driving by a humanoid robot

Abstract: Enabling a humanoid robot to drive a car requires the development of a set of basic primitive actions. These include walking to the vehicle, manually controlling its commands (e.g., ignition, gas pedal, and steering) and moving with the whole body to ingress/egress the car. We present a sensor‐based reactive framework for realizing the central part of the complete task, consisting of driving the car along unknown roads. The proposed framework provides three driving strategies by which a human supervisor can te… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
11
0

Year Published

2017
2017
2023
2023

Publication Types

Select...
4
3
2

Relationship

4
5

Authors

Journals

citations
Cited by 22 publications
(11 citation statements)
references
References 49 publications
0
11
0
Order By: Relevance
“…In this case, we use the acceleration measured by the IMU in the filter prediction, to propagate an initial estimation of the robot velocity. Filter updates are obtained through the robot differential kinematics, relying on encoders data, and an estimation of the robot velocity based on optical flow [15] [16]. This last estimation comes at no additional computational cost since the optical flow is also computed to detect obstacles (see Sect.…”
Section: A Kalman Filter Designmentioning
confidence: 99%
“…In this case, we use the acceleration measured by the IMU in the filter prediction, to propagate an initial estimation of the robot velocity. Filter updates are obtained through the robot differential kinematics, relying on encoders data, and an estimation of the robot velocity based on optical flow [15] [16]. This last estimation comes at no additional computational cost since the optical flow is also computed to detect obstacles (see Sect.…”
Section: A Kalman Filter Designmentioning
confidence: 99%
“…What makes humanoids a plausible perspective for their deployment in aerospace -or other large-scale productsmanufacturing, is their ability to use multi-contact technology, which has been the focus of our research and development in the past years [7][6] [5], see also 4 . Indeed, humanoid locomotion in cluttered environment exploits possible sequence of contact creations and removals between any part of the robot and the environment to plan motions.…”
Section: Task-aware Contact Planningmentioning
confidence: 99%
“…Recently the DARPA robotic challenge 2 opened potential applications in rescue and disaster operations. Yet the contest brought into light the gap that remains to overcome in order to efficiently deploy such a technology outdoor and achieve complex tasks such as driving [4] or ladder climbing [5]. During the two previous years, we focused our efforts on applications of humanoids in manufacturing.…”
Section: Introductionmentioning
confidence: 99%
“…It has been shown that those robots are able to execute tasks which are mostly done by humans in today's industrial world. Their anthropomorphic structure and diverse sensory feedback enables walking on uneven terrains [1], climbing ladders [2], driving cars [3] and many other tasks as seen e.g. in the DARPA robotics challenge.…”
Section: Introductionmentioning
confidence: 99%