The Agents

Although a detailed description of the agents was already given in Chapter 4, as well as the description of the differences between the simulated system and the final system, (given at the beginning of this chapter), we review the parameters of each of the agents:

• Target Tracker ( $\alpha,\beta,\kappa_1,\kappa_2$)
  • $\alpha$: controls how rapidly the bids for moving towards the target decrease,      $bid(move(\theta)) = \kappa_{1}(1 - I_{a}^{1/\alpha})$; high values of $\alpha$ make bids increase fast, while low values make bids increase slowly

  • $\beta$: controls the shape of the imprecision function, $I_{a}=\left(\frac{\epsilon_{\theta}}{2\pi}\right)^{\beta}$; high values make it increase slowly, while low values make it increase fast

  • $\kappa1$: maximum value for moving actions bids

  • $\kappa2$: maximum value for looking actions bids

• Distance Estimator ( $\kappa,\phi,\delta$)
  • $\kappa$: controls the shape of the distance imprecision function, $I_{d} = 1 - {1/e^{\kappa\epsilon_{t}}}$; high values of $\kappa$ make the imprecision grow fast, while low values make it increase slowly

  • $\phi,\delta$: controls the at target computation; it considers that the robot has reached the target if the upper bound of the $\alpha$-cut of level $\phi$ of the fuzzy number modeling the distance to the target is less than $\delta$ times the body size of the robot

• Risk Manager ( $\gamma_A,\gamma_B,\gamma_r$)
  • $\gamma_A,\gamma_B$: control the relative importance of the position of landmarks, ahead and around, respectively, used in the risk computation,
    
    $$R=1 - \min \left(1, q_{A} {\left(\frac{\vert A \vert}{6}\ri... ...}{\left(\frac{\vert B \vert}{6}\right)}^{\gamma_{B}}\right)$$
    
    

  • $\gamma_r$: maximum value for looking actions bids

• Rescuer ( $\overline{I}_{a},\overline{R}$)
  • $\overline{I}_{a}$: imprecision threshold, above which this agent gets active

  • $\overline{R}$: risk threshold, above which this agent gets active