The Amazon Robotics Challenge was an event created by Amazon to bring robotics teams together and try to push forward the research on robotics automation related to warehouse logistics. The challenge consists of two tasks. The picking task requires a fully autonomous robotic system to remove target objects from a shelving unit into a tote. The stowing task requires placing objects from a tote into the shelving unit. The purpose of this thesis is to present state-of-the-art approaches related to motion, grasp and task planning, pose estimation solutions, and how different end-effector modalities can affect the performance of the autonomous system. Two grasp planning and three task planning approaches are evaluated and combined with a PRM* motion planner in the context of the Amazon Robotics Challenge tasks.