Perception-aware planning for differentially flat robots

The central question to this thesis can be stated as follows: “Can we design computationally efficient algorithms that are capable of robustly navigating complex environments and unstructured environments at operational speeds." Visual inertial navigation in perceptually degraded environments is a challenging problem for robotic vehicles. With a camera, inertial measurement unit (IMU) pairing being ubiquitous to most consumer electronics, they form an ideal pairing for applications on the edge and have found applications ranging from large-scale search and rescue, autonomous driving to home robots such as robotic vacuum cleaners. In general, the navigation problem for robots can be written in the form of the sense-think-act framework for autonomy. The “sensing" part is typically performed in this context as bearing measurements to visually salient locations in the environment; the “planning" part then uses the estimate of the ego-state from the sensors and produces a (compactly represented) trajectory from the current location to the goal. Finally, the “act" or controller follows the plan. This division leaves several interesting problems at the intersection of the parts of the framework. For instance, consider the problem of navigating in a relatively unknown environment; if the future percepts are not carefully planned, it is possible to enter a room with very few visual features that degrade the quality of state estimation, which in turn can result in poor closed-loop performance. Quadrotors are a class of robots that dictate further constraints on their sensors, namely size and weight. These constraints make camera-IMU pairings ideal for this type of aerial vehicle and bring further interesting challenges in terms of computational load for embedded systems. To this end, we first study the problem of modeling visibility on the camera canvas and incorporating these heuristics as an optimal-control problem. We then study the problem of optimizing the robot speed along the path with visible features such that the traversal time is minimized and the constraints are satisfied. As we hit the limit of optimization capability in a model-based fashion, we employ machine learning to jointly optimize the speed, uncertainty along the trajectory in a numerically stable fashion.

Name thesis:degree_name

Doctoral

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Aeronautics and Astronautics

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2024

Author dc:creator

• Murali, Varun

Advisor dc:contributor.advisor

• Karaman, Sertac

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright retained by author(s)

Licence dc:rights.uri

• https://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/153794

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/153794