Agriculture Reference
In-Depth Information
applications, but have not performed well in sparsely populated crops. Their reliability
reduces with low lighting, shadows, dust, and fog. Benson et al. (2001) overcame this by
using artificial lighting. Laser radar has been used for ranging and obstacle avoidance.
It has higher resolution than ultrasonic sensing, and requires fewer computations than
vision. Its performance degrades with dust and rain like vision, and it is costlier than
ultrasound. It provides planar data of the path, but can generate 3-D data by rotating the
laser source to give a 3-D view. O'Conner et al. (1995) found that sensor data are noisy,
and can be filtered using Kalman filters to obtain robust sensor fusion.
Steering control is a major factor for accurate guidance. PID (proportional, integral,
derivative) control has given satisfactory performance (Zhang et al., 1999). Neural net-
works have the inherent disadvantage of learning only what the driver does, so they are
not robust. Behavior-based control is a new development that has been successfully used
in small mobile robots. A behavior-based system in combination with a real-time control
system is expected to do well in vehicle guidance. Fuzzy control has recently been tried
with results comparable with PID (Benson et al., 2001). Senoo et al. (1992) have pointed
out that the fuzzy controller could achieve better tracking performance than the PID
controller. It has wider adaptability to all kinds of inputs. Qiu et al. (2001) verified that the
fuzzy steering control provided a prompt and accurate steering rate control on the tractor.
Kodagoda et al. (2002) found fuzzy control to be better than PID for longitudinal control.
PID was also found to have large chatter, high saturation. A combination of fuzzy and
PID control holds significant promise (Benson et al., 2001). Efficient guidance can be
achieved using a fuzzy-PID control system with vision, laser radar, and IMU as sensors.
Subramanian et al. (2006, 2009) developed a successful in-the-row autoguidance sys-
tems for citrus groves relying on data fused from machine vision, laser radar, and IMU,
without DGPS. This control implementation is demonstrated in Figure 7.38.
IMU
Windows
Linux
Steering
controller
Pure pursuit
steering
CAN
Steering
Ladar
Error
Speed
Steering
Kalman
Filter
Sensor
Fusion
Speed
control
DC motor
Headland
navigation
Speed
Speed
Dead
reckoning
Vision
Brake
Position
Encoder
FIGURE 7.38
Autonomous vehicle control architecture. (From Subramanian, V. et al.,
Tra ns.
ASABE
, 52, 5, 1-12, 2005;
Comput. Electron. Agric.
,
53, 130-143, 2006. With permission.)
