IPAB Workshop-05/11/2020

Oguzhan Cebe

Title: Online Dynamic Trajectory Optimization and Control for a   Quadruped Robot Abstract: Legged robot locomotion requires the planning of stable reference  trajectories, especially while traversing uneven terrain. The   proposed trajectory  optimization  framework  is capable  of   generating  dynamically  stable  base  and  footstep trajectories  for    multiple  steps.  The  locomotion  task  can  be defined  with   contact  locations, base  motion or both, making the algorithm   suitable for multiple scenarios (e.g.,  presence  of moving   obstacles). The planner uses a simplified  momentum-based task space  model for the robot dynamics, allowing computation times that are fast  enough for online  replanning. This fast planning capability also  enables the quadruped to  accommodate for drift and environmental  changes.

Hanz Cuevas Velasquez

Title: Joint semantic segmentation and disparity learning

Abstract: Disparity estimation and semantic segmentation are two fundamental problems in computer vision. The goal of disparity estimation is to obtain the corresponding pixels from a rectified pair of images. On the other hand, semantic segmentation is used to assign class labels to each pixel in the image. These two methods are highly used in scene understanding, autonomous driving and robotics. However, executing the state-of-the-art methods of both areas together involves a long computation run-time, which is prohibitively expensive in these systems. Therefore, a method that combines both tasks into a single model reduces computation and allows it to be embedded in portable devices or executed in real-time. We approach this problem through multi-task learning, our method focuses on sharing the specific feature knowledge between tasks in a progressive manner, which improves learning efficiency and prediction accuracy for each task.