The IKEA Furniture Assembly Environment is one of the first benchmarks for testing and accelerating the automation of complex manipulation tasks. The environment is designed to advance reinforcement learning from simple toy tasks to complex tasks requiring both long-term planning and sophisticated low-level control. Our environment supports over 80 different furniture models, Sawyer and Baxter robot simulation, and domain randomization. The IKEA Furniture Assembly Environment is a testbed for methods aiming to solve complex manipulation tasks. The environment is publicly available at https://clvrai.com/furniture. Figure 1: The IKEA Furniture Assembly Environment is a furniture assembly simulator. It contains diverse sets of furniture models and robots, and supports various background, lighting, and textures.

No abstract

No abstract

Training visuomotor robot controllers from scratch on a new robot typically requires generating large amounts of robot-specific data. Could we leverage data previously collected on another robot to reduce or even completely remove this need for robot-specific data? We propose a "robot-aware" solution paradigm that exploits readily available robot "self-knowledge" such as proprioception, kinematics, and camera calibration to achieve this. First, we learn modular dynamics models that pair a transferable, robot-agnostic world dynamics module with a robot-specific, analytical robot dynamics module. Next, we set up visual planning costs that draw a distinction between the robot self and the world. Our experiments on tabletop manipulation tasks in simulation and on real robots demonstrate that these plug-in improvements dramatically boost the transferability of visuomotor controllers, even permitting zero-shot transfer onto new robots for the very first time. Project website: https://hueds.github.io/rac/ Preprint. Under review.

As oceanic research continues to grow for scientific and commercial purposes, demand for knowledge pertaining to the ocean continues to increase. This research investigates a Wave Glider that was developed by engineers for the purpose of collecting data from oceans. The Wave Glider is a novel two-body unmanned surface vehicle (USV). Compared to traditional unmanned surface vehicles, the Wave Glider has the unique advantage of long term navigation ability. With this advantage, the vehicle can complete missions which require long-term ocean trials.This research project is focused on studying the feasibility of improving the design and operation of the Wave Glider and further developing its capabilities. To obtain real-time data, a scale model based on the original Wave Glider design has been manufactured. Improvement to the original design has already been achieved with regards to improving the stability of the wings. Based on a literature review, some concern was found over its robustness when trialing and this is addressed in this paper. Throughout this research, Computational Fluid Dynamics (CFD) analysis has been done on the Wave Glider to ensure optimum efficiency. Furthermore, CAD design of the scaled model has been reviewed to ensure success in manufacturing and operation. The Wave Glider model will be used to collect real time data for comparison with simulated data. Additional improvements included in the model will also be discussed.