Improved Activity Forecasting for Generating Trajectories
This work addresses trajectory generation for seabird monitoring, but it appears incremental as it builds on existing inverse reinforcement learning with specific modifications.
The paper tackles the problem of generating realistic trajectories for seabirds by proposing an improved inverse reinforcement learning method that modifies the reward function with Lp norm and introduces convolutional value iteration. Experimental results on 53 seabird trajectories show the method achieves the best MHD error and fastest performance compared to previous works.
An efficient inverse reinforcement learning for generating trajectories is proposed based of 2D and 3D activity forecasting. We modify reward function with $L_p$ norm and propose convolution into value iteration steps, which is called convolutional value iteration. Experimental results with seabird trajectories (43 for training and 10 for test), our method is best in terms of MHD error and performs fastest. Generated trajectories for interpolating missing parts of trajectories look much similar to real seabird trajectories than those by the previous works.