An Approach to Task Representation Based on Object Features and Affordances

. 2022 Aug 17;22(16):6156. doi: 10.3390/s22166156

Algorithm 1 Task understanding algorithm
Input
$P c_{1}$ point cloud of the before-scene
$P c_{2}$ point cloud of the after-scene
Output
$T r$ Task description
1: $\begin{array}{l} P c_{1} \leftarrow P r e P r o c e s s (P c_{1}), P c_{2} \leftarrow P P (P c_{2}) \end{array}$ 2: $\begin{array}{l} S e_{1} \leftarrow {}, S r_{1} \leftarrow {}, S e_{2} \leftarrow {}, S r_{2} \leftarrow {} & ▹ empty sets \end{array}$ 3: $\begin{array}{l} S e_{1} + = D e t e c t O b j e c t s (P c_{1}), S e_{2} + = D e t e c t O b j e c t s (P c_{2}) & ▹ adding elements to sets \end{array}$ 4: $\begin{array}{l} S e_{1} + = D e t e c t F e a t u r e s (S e), S e_{2} + = D e t e c t F e a t u r e s (S e) \end{array}$ 5: $\begin{array}{l} S r_{1} + = D e t e c t R e l a t i o n s (S e), S r_{2} + = D e t e c t R e l a t i o n s (S e) \end{array}$ 6: $\begin{array}{l} S d_{1} \leftarrow D e s c r i b e S c e n e (S e_{1}, S r_{1}), S d_{2} \leftarrow D e s c r i b e S c e n e (S e_{2}, S r_{1} 2) \end{array}$ 7: $\begin{array}{l} T r \leftarrow D e s c r i b e T a s k (S d_{1}, S d_{2}) \end{array}$