Felipe Polido
Your Personal Robotics Engineer

Robotics Software Developer Engineer working in general Manipulation and Grasping problems for the Advanced Robotics group.

Software Engineer in the Dynamic Legged Systems (DLS) laboratory, which performs research and development for the design and control of high-performance and versatile legged robots. Developed a modular architecture to handle support and transition between a range of low and high-level controllers.

The architecture interfaces between different simulators (such as Gazebo and SL) and the real-hardware. It creates a range of common interfaces and utilities between the controllers (such as logging and visualization tools), handles transition between different sensor inputs( such as VICON Motion Capture, LIDAR, etc..) and state-estimation techniques ( EKF, Pronto, etc..). Coordinate and integrate the development of the laboratory efforts towards a set of cohesive software utilities.

Develop, maintain and repair software at all levels, from embedded firmware, through low-level controller, to high-level motion planning. Work daily on multiple state-of-the-art hydraulic robots including the 12 DoF quadrupeds HyQ and HyQ2Max, and 6 DoF HyA arm. Systems operate in a Real-time Xenomai Linux Kernel. Architecture built heavily on ROS, Gazebo, SL simulator, LCM, RViZ, KDL, RBDL, etc.

Manipulation leader for the WPI-CMU's DARPA Robotics Challenge (DRC) team. Extensive experience with the 30 DoF Boston Dynamics Atlas humanoid robot. Research and implementation of state-of-the-art full-body motion planning libraries including MoveIt (OMPL), CHOMP, CBiRRT2 and TrajOpt, with emphasis on maintaining multiple constraints simultaneously (balance, collision-avoidance, end-effector pose, etc..).

Integrate systems from perception to the full-body manipulation controller based on combined Inverse Kinematics and Inverse Dynamics control loops resolved using a Quadratic Programming approach to realize full-body path plans on the Atlas robot.

Coordinate a team of graduate and undergraduate students to develop, test and integrate the algorithms above towards a competitive entry for the DRC.

Manipulation leader for the WPI-CMU's DARPA Robotics Challenge trials team. Development of multiple manipulation approaches including upper-body 6 and 9 DoF path planners based on ROS MoveIt (OMPL), as well as full-body controllers based on a combined Inverse Dynamics and Inverse Kinematics Quadratic Programing technique.

Design of an 6 DoF planning and motion controller from scratch. Experimentation with varied user interface devices for manipulation including Razer Hydra and the surgical robot daVinci operator master unit. Comparison and development of multiple grasping techniques using iRobot, Sandia, and Robotiq 3-finger robotic hands.

Task leader for the drill and valve tasks. The former involves the Atlas robot picking up a rotary tool from a shelf, walking to a vertical Drywall sheet and cutting a pre-determined polygon. The latter involves closing three wall-mounted industrial size valves.

Designed and implemented a miniature self-contained wireless sensor device for mesh ad-hoc network deployment, mainly for sports related secondary-concussion detection. Solely responsible for development from concept to product, including embedded and front-end software, PCB design, manufacturing, and assembly.

Developed a robotic entry for the 18th Annual Intelligent Ground Vehicle Competition. The vehicle had a custom aluminum chassis and fused the sensory input from a LIDAR, stereo vision cameras, 6 DOF Inertial Measurement Unit, and GPS signal to drive autonomously through a complex outdoor obstacle course using a SLAM algorithm implementation in ROS.