Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Modeling of a fixed wing UAV.

More »

Fig 1 Expand

Fig 2.

Track followed by fixed wing UAV.

More »

Fig 2 Expand

Fig 3.

Working of airspeed and altitude controller.

More »

Fig 3 Expand

Fig 4.

Working of heading controller.

More »

Fig 4 Expand

Fig 5.

Working of attitude controller.

More »

Fig 5 Expand

Fig 6.

DDPG algorithm structure.

More »

Fig 6 Expand

Fig 7.

TD3 algorithm structure.

More »

Fig 7 Expand

Fig 8.

PPO algorithm structure.

More »

Fig 8 Expand

Fig 9.

TRPO algorithm structure.

More »

Fig 9 Expand

Fig 10.

SAC algorithm structure.

More »

Fig 10 Expand

Table 1.

Strengths and limitations of RL algorithms.

More »

Table 1 Expand

Table 2.

Training process for RL agents.

More »

Table 2 Expand

Table 3.

Evaluation criteria for RL agents.

More »

Table 3 Expand

Table 4.

Hyperparameters for all agents.

More »

Table 4 Expand

Fig 11.

The Altitude Control (left) and Training Curve (right) obtained on DDPG agent.

More »

Fig 11 Expand

Fig 12.

The Heading Control (left) and Roll Control (right) obtained on DDPG agent.

More »

Fig 12 Expand

Fig 13.

The Altitude Control (left) and Training Curve (right) obtained on TRPO agent.

More »

Fig 13 Expand

Fig 14.

The Heading Control (left) and Roll Control (right) obtained on TRPO agent.

More »

Fig 14 Expand

Fig 15.

The Altitude Control (left) and Training Curve (right) obtained on PPO agent.

More »

Fig 15 Expand

Fig 16.

The Heading Control (left) and Roll Control (right) obtained on PPO agent.

More »

Fig 16 Expand

Fig 17.

The Altitude Control (left) and Training Curve (right) obtained on TD3 agent.

More »

Fig 17 Expand

Fig 18.

The Heading Control (left) and Roll Control (right) obtained on TD3 agent.

More »

Fig 18 Expand

Fig 19.

The Altitude Control (left) and Training Curve (right) obtained on SAC agent.

More »

Fig 19 Expand

Fig 20.

The Heading Control (left) and Roll Control (right) obtained on SAC agent.

More »

Fig 20 Expand

Fig 21.

The altitude control for PID controller.

More »

Fig 21 Expand

Fig 22.

The Heading Control (left) and Roll Control (right) of PID controller.

More »

Fig 22 Expand

Fig 23.

The deflection of control surfaces over time.

More »

Fig 23 Expand

Fig 24.

Comparison of RL agent and PID response for altitude controller.

More »

Fig 24 Expand

Fig 25.

Comparison of RL agent and PID response for heading controller.

More »

Fig 25 Expand

Fig 26.

Comparison of RL agent and PID response for roll controller.

More »

Fig 26 Expand

Table 5.

Comparison of RL agents.

More »

Table 5 Expand

Table 6.

Training time, total steps, and step efficiency of RL agents.

More »

Table 6 Expand

Table 7.

Comparison of PID and RL agents.

More »

Table 7 Expand