PhD Thesis Defense
Carnegie Mellon University
Heuristics for routing and scheduling of Spatio-temporal type problems in industrial environments
Abstract: Spatio-temporal problems are fairly common in industrial environments. In practice, these problems come with different characteristics and are often very hard to solve optimally. So, practitioners prefer to develop heuristics that exploit mathematical structure specific to the problem for obtaining good performance. In this thesis, we will present work on heuristics for 3 different [...]
Carnegie Mellon University
Relationships in instance segmentation and anomaly detection
Abstract: This thesis primarily covers work on two different tasks in computer vision: (1) anomaly detection and (2) instance segmentation. Anomaly detection is an underexplored unsupervised problem that has existed in many fields. On the other hand, instance (and panoptic) segmentation is a supervised problem that can leverage the powerful data and key developments from [...]
Carnegie Mellon University
Dynamical Model Learning and Inversion for Aggressive Quadrotor Flight
Abstract: Quadrotor applications have seen a surge recently and many tasks require precise and accurate controls. Flying fast is critical in many applications and the limited onboard power source makes completing tasks quickly even more important. Staying on a desired course while traveling at high speeds and high accelerations is difficult due to complex and [...]
Carnegie Mellon University
Person Transfers Between Multiple Service Robots
Abstract: As more service robots are deployed in the world, human-robot interaction will not be limited to one-to-one interactions between users and robots. Instead, users will likely have to interact with multiple robots, simultaneously or sequentially, throughout their day to receive services and complete different tasks. In this thesis, I describe work in which my [...]
Carnegie Mellon University
Understanding, Exploiting and Improving Inter-view Relationships
Abstract: Multi-view machine learning has garnered substantial attention in various applications over recent years. Many such applications involve learning on data obtained from multiple heterogeneous sources of information, for example, in multi-sensor systems such as self-driving cars, or monitoring intensive care patient vital signs at their bed-side. Learning models for such applications can often benefit [...]
Carnegie Mellon University
Human-in-the-loop Control of Mobile Robots
Abstract: Human-in-the-loop control for mobile robots is an important aspect of robot operation, especially for navigation in unstructured environments or in the case of unexpected events. However, traditional paradigms of human-in-the-loop control have relied heavily on the human to provide precise and accurate control inputs to the robot, or reduced the role of the human [...]
Carnegie Mellon University
Planning and Execution using Inaccurate Models with Provable Guarantees on Task Completeness
Abstract: Modern planning methods are effective in computing feasible and optimal plans for robotic tasks when given access to accurate dynamical models. However, robots operating in the real world often face situations that cannot be modeled perfectly before execution. Thus, we only have access to simplified but potentially inaccurate models. This imperfect modeling can lead [...]
Carnegie Mellon University
Development of an Agile and Dexterous Balancing Mobile Manipulator Robot
Abstract: This thesis focuses on designing and controlling a dynamically stable shape-accelerating dual-arm mobile manipulator, the Carnegie Mellon University (CMU) ballbot. The CMU ballbot is a human-sized dynamically stable mobile robot that balances on a single spherical wheel. We describe the development of a pair of seven-degree-of-freedom (DOF) humanoid arms. The new 7-DOF arm pair [...]
Carnegie Mellon University
Learning and Inference in Factor Graphs with Applications to Tactile Perception
Abstract: Factor graphs offer a flexible and powerful framework for solving large-scale, nonlinear inference problems as encountered in robot perception and control. Typically, these methods rely on handcrafted models that are efficient to optimize. However, robots often perceive the world through complex, high-dimensional sensor observations. For instance, consider a robot manipulating an object in hand [...]
Carnegie Mellon University
Unified Simulation, Perception, and Generation of Human Behavior
Abstract: Understanding and modeling human behavior is fundamental to almost any computer vision and robotics applications that involve humans. In this thesis, we take a holistic approach to human behavior modeling and tackle its three essential aspects --- simulation, perception, and generation. Throughout the thesis, we show how the three aspects are deeply connected and [...]
Carnegie Mellon University
Search Algorithms and Search Spaces for Neural Architecture Search
Abstract: Neural architecture search (NAS) is recently proposed to automate the process of designing network architectures. Instead of manually designing network architectures, NAS automatically finds the optimal architecture in a data-driven way. Despite its impressive progress, NAS is still far from being widely adopted as a common paradigm for architecture design in practice. This thesis [...]
Carnegie Mellon University
Self-Improving 3D Scene Representations
Abstract: Most computer vision models in deployment today are not continually learning. Instead, they are in a “test” mode, where they will behave the same way perpetually, until they are replaced by newer models. This is a problem, because it means the models may perform poorly as soon as their “test” environment diverges from their [...]
Carnegie Mellon University
Direct-drive Hands: Making Robot Hands Transparent and Reactive to Contacts
Abstract: Industrial manipulators and end-effectors are a vital driver of the automation revolution. These robot hands, designed to reject disturbances with stiffness and strength, are inferior to their human counterparts. Human hands are dexterous and nimble effectors capable of a variety of interactions with the environment. Through this thesis we wish to answer a question: [...]
Carnegie Mellon University
Resource-Constrained Learning and Inference for Visual Perception
Abstract: We have witnessed rapid advancement across major computer vision benchmarks over the past years. However, the top solutions' hidden computation cost prevents them from being practically deployable. For example, training large models until convergence may be prohibitively expensive in practice, and autonomous driving or augmented reality may require a reaction time that rivals that [...]
Carnegie Mellon University
Physical Interaction and Manipulation of the Environment using Aerial Robots
Abstract: The physical interaction of aerial robots with their environment has countless potential applications and is an emerging area with many open challenges. Fully-actuated multirotors have been introduced to tackle some of these challenges. They provide complete control over position and orientation and eliminate the need for attaching a multi-DoF manipulation arm to the robot. [...]
Carnegie Mellon University
Visual Representation and Recognition without Human Supervision
Abstract: The advent of deep learning based artificial perception models has revolutionized the field of computer vision. These methods take advantage of the ever growing computational capacity of machines and the abundance of human-annotated data to build supervised learners for a wide-range of visual tasks. However, the reliance on human-annotated is also a bottleneck for [...]
Carnegie Mellon University
Learning Multi-Modal Navigation in Unstructured Environments
Abstract: A robot that operates efficiently in a team with humans in an unstructured outdoor environment must translate commands into actions from a modality intuitive to its operator. The robot must be able to perceive the world as humans do so that the actions taken by the robot reflect the nuances of natural language and [...]
Carnegie Mellon University
Towards Modular and Differentiable Autonomous Driving
Abstract: The classical "modular and cascaded" autonomy stack (object detection, tracking, trajectory prediction, then planning and control) has been widely used for interactive autonomous systems such as self-driving cars due to its interpretability and fast development cycle. In this thesis, we advocate the use of such a modular stack but improve its accuracy and robustness [...]
Carnegie Mellon University
Control Input and Natural Gaze for Goal Prediction in Shared Control
Abstract: Teleoperated systems are used widely in deployed robots today, for such tasks as space exploration, disaster recovery, or assisted manipulation. However, teleoperated systems are difficult to control, especially when performing high-dimensional, contact-rich tasks like manipulation. One approach to ease teleoperated manipulation is shared control; this strategy combines the user's direct control input with an [...]
Carnegie Mellon University
Liquid Metal Actuators
Abstract: This thesis contributes to the field of soft actuators by introducing a generalized framework of actuators from liquid metals. The evolution of robotic actuators has enabled robots to achieve a diversity of motions. Like natural muscles, which converts chemical energy into mechanical work in response to electrical stimuli from the nervous system, actuators are [...]
Carnegie Mellon University
Learning Structured World Model for Deformable Object Manipulation
Abstract: Manipulation of deformable objects challenges common assumptions in robotic manipulation, such as low-dimension state representation, known dynamics, and minimal occlusion. Deformable objects have high intrinsic state representation, complex dynamics with high degrees of freedom, and severe self-occlusion. These properties make them difficult for state estimation and planning. In this thesis, we introduce benchmarks and [...]
Carnegie Mellon University
Object Pose Estimation without Direct Supervision
Abstract: Currently, robot manipulation is a special purpose tool, restricted to isolated environments with a fixed set of objects. In order to make robot manipulation more general, robots need to be able to perceive and interact with a large number of objects in cluttered scenes. Traditionally, object pose has been used as a representation to [...]
Carnegie Mellon University
Heuristic Search Based Planning by Minimizing Anticipated Search Efforts
Abstract: We focus on relatively low dimensional robot motion planning problems, such as planning for navigation of a self-driving vehicle, unmanned aerial vehicles (UAVs), and footstep planning for humanoids. In these problems, there is a need for fast planning, potentially compromising the solution quality. Often, we want to plan fast but are also interested in [...]
Carnegie Mellon University
Accelerating Numerical Methods for Optimal Control
Abstract:Â Many modern control methods, such as model-predictive control, rely heavily on solving optimization problems in real time. In particular, the ability to efficiently solve optimal control problems has enabled many of the recent breakthroughs in achieving highly dynamic behaviors for complex robotic systems. The high computational requirements of these algorithms demand novel algorithms tailor-suited [...]
Carnegie Mellon University
3D Reconstruction using Differential Imaging
Abstract: 3D reconstruction has been at the core of many computer vision applications, including autonomous driving, visual inspection in manufacturing, and augmented and virtual reality (AR/VR). Because monocular 3D sensing is fundamentally ill-posed, many techniques aiming for accurate reconstruction use multiple captures to solve the inverse problem. Depending on the amount of change in these [...]
Learning with Structured Priors for Robust Robot Manipulation
Abstract: Robust and generalizable robots that can autonomously manipulate objects in semi-structured environments can bring material benefits to society. Data-driven learning approaches are crucial for enabling such systems by identifying and exploiting patterns in semi-structured environments, allowing robots to adapt to novel scenarios with minimal human supervision. However, despite significant prior work in learning for [...]
Carnegie Mellon University
Self-Supervising Occlusions For Vision
Abstract: Virtually every scene has occlusions. Even a scene with a single object exhibits self-occlusions - a camera can only view one side of an object (left or right, front or back), or part of the object is outside the field of view. More complex occlusions occur when one or more objects block part(s) of [...]
Carnegie Mellon University
Learning with Diverse Forms of Imperfect and Indirect Supervision
Abstract: Powerful Machine Learning (ML) models trained on large, annotated datasets have driven impressive advances in fields including natural language processing and computer vision. In turn, such developments have led to impactful applications of ML in areas such as healthcare, e-commerce, and predictive maintenance. However, obtaining annotated datasets at the scale required for training high [...]
Computational Interferometric Imaging
Abstract: Imaging systems typically accumulate photons that, as they travel from a light source to a camera, follow multiple different paths and interact with several scene objects. This multi-path accumulation process confounds the information that is available in captured images about the scene and makes using these images to infer properties of scene objects, such [...]
Neural Radiance Fields with LiDAR Maps
Abstract: Maps, as our prior understanding of the environment, play an essential role for many modern robotic applications. The design of maps, in fact, is a non-trivial art of balance between storage and richness. In this thesis, we explored map compression for image-to-LiDAR registration, LiDAR-to-LiDAR map registration, and image-to-SfM map registration, and finally, inspired by [...]
Carnegie Mellon University
System Identification and Control of Multiagent Systems Through Interactions
Abstract: This thesis investigates the problem of inferring the underlying dynamic model of individual agents of a multiagent system (MAS) and using these models to shape the MAS's behavior using robots extrinsic to the MAS. We investigate (a) how an observer can infer the latent task and inter-agent interaction constraints from the agents' motion and [...]
Carnegie Mellon University
Parallelized Search on Graphs with Expensive-to-Compute Edges
Abstract: Search-based planning algorithms enable robots to come up with well-reasoned long-horizon plans to achieve a given task objective. They formulate the problem as a shortest path problem on a graph embedded in the state space of the domain. Much research has been dedicated to achieving greater planning speeds to enable robots to respond quickly [...]
Carnegie Mellon University
Visual Dataset Pipeline: From Curation to Long-Tail Learning
Abstract: Computer vision models have proven to be tremendously capable of recognizing and detecting several real-world objects: cars, people, pets. These models are only possible due to a meticulous pipeline where a task and application is first conceived followed by an appropriate dataset curation that collects and labels all necessary data. Commonly, studies are focused [...]
Carnegie Mellon University
Optimization of Small Unmanned Ground Vehicle Design using Reconfigurability, Mobility, and Complexity
Abstract: Unmanned ground vehicles are being deployed in increasingly diverse and complex environments. With modern developments in sensing and planning, the field of ground vehicle mobility presents rich possibilities for mechanical innovations that may be especially relevant for unmanned systems. In particular, reconfigurability may enable vehicles to traverse a wider set of terrains with greater [...]
Carnegie Mellon University
Towards Reconstructing Non-rigidity from Single Camera
Abstract: In this talk we will discuss how to infer 3D from images captured by a single camera, without assuming the target scenes / objects being static. The non-static setting makes our problem ill-posed and challenging to solve, but is vital in practical applications where target-of-interest is non-static. To solve ill-posed problems, the current trend [...]
Large Scale Dense 3D Reconstruction via Sparse Representations
Abstract: Dense 3D scene reconstruction is in high demand today for view synthesis, navigation, and autonomous driving. A practical reconstruction system inputs multi-view scans of the target using RGB-D cameras, LiDARs, or monocular cameras, computes sensor poses, and outputs scene reconstructions. These algorithms are computationally expensive and memory-intensive due to the presence of 3D data. [...]
From Reinforcement Learning to Robot Learning: Leveraging Prior Data and Shared Evaluation
Abstract: Unlike most machine learning applications, robotics involves physical constraints that make off-the-shelf learning challenging. Difficulties in large-scale data collection and training present a major roadblock to applying today’s data-intensive algorithms. Robot learning has an additional roadblock in evaluation: every physical space is different, making results across labs inconsistent. Two common assumptions of the robot [...]
Building 4D Models of Objects and Scenes from Monocular Videos
Abstract: We explore how to infer the time-varying 3D structures of generic, deformable objects, and dynamic scenes from monocular videos. A solution to this problem is essential for virtual reality and robotics applications. However, inferring 4D structures given 2D observations is challenging due to its under-constrained nature. In a casual setup where there is neither [...]
Learning via Visual-Tactile Interaction
Abstract: Humans learn by interacting with their surroundings using all of their senses. The first of these senses to develop is touch, and it is the first way that young humans explore their environment, learn about objects, and tune their cost functions (via pain or treats). Yet, robots are often denied this highly informative and [...]
Redefining the Perception-Action Interface: Visual Action Representations for Contact-Centric Manipulation
Abstract: In robotics, understanding the link between perception and action is pivotal. Typically, perception systems process sensory data into state representations like segmentations and bounding boxes, which a planner uses to plan actions. However, this state estimation approach can fail in environments with partial observability, and in cases with challenging object properties like transparency and deformability. [...]
Multi-Human 3D Reconstruction from Monocular Videos
Abstract: We study the problem of multi-human 3D reconstruction from videos captured in the wild. Human movements are dynamic, and accurately reconstructing them in various settings is crucial for developing immersive social telepresence, assistive humanoid robots, and augmented reality systems. However, creating such a system requires addressing fundamental issues with previous works regarding the data [...]
How I Learned to Love Blobs: The Power of Gaussian Representations in Differentiable Rendering and Optimization
Abstract: In this thesis, we explore the use of Gaussian Representations in multiple application areas of computer vision and robotics. In particular, we design a ray-based differentiable renderer for 3D Gaussians that can be used to solve multiple classic computer vision problems in a unified manner. For example, we can reconstruct 3D shapes from color, [...]
Towards Photorealistic Dynamic Capture and Animation of Human Hair and Head
Abstract: Realistic human avatars play a key role in immersive virtual telepresence. To reach a high level of realism, a human avatar needs to faithfully reflect human appearance. A human avatar should also be drivable and express natural motions. Existing works have made significant progress in building drivable realistic face avatars, but they rarely include [...]
Modeling Dynamic Clothing for Data-Driven Photorealistic Avatars
Abstract: In this thesis, we aim to build photorealistic animatable avatars of humans wearing complex clothing in a data-driven manner. Such avatars will be a critical technology to enable future applications such as immersive telepresence in Virtual Reality (VR) and Augmented Reality (AR). Existing full-body avatars that jointly model geometry and view-dependent texture using Variational [...]
Manipulation Among Movable Objects for Pick-and-Place Tasks in Cluttered 3D Workspaces
Abstract: In cluttered real-world workspaces, simple pick-and-place tasks for robot manipulators can be quite challenging to solve. Often there is no collision-free trajectory that allows the robot to grasp and extract a desired object from the scene. This requires motion planning algorithms to reason about rearranging some of the “movable” clutter in the scene so [...]
Generalizable Dexterity with Reinforcement Learning
Abstract: Dexterity, the ability to perform complex interactions with the physical world, is at the core of robotics. However, existing research in robot manipulation has been focused on tasks that involve limited dexterity, such as pick-and-place. The motor skills of the robots are often quasi-static, have a predefined or limited sequence of contact events, and [...]
Sample-Efficient Reinforcement Learning with applications in Nuclear Fusion
Abstract: In many practical applications of reinforcement learning (RL), it is expensive to observe state transitions from the environment. In the problem of plasma control for nuclear fusion, the motivating example of this thesis, determining the next state for a given state-action pair requires querying an expensive transition function which can lead to many hours [...]
Social Navigation with Pedestrian Groups
Abstract: Autonomous navigation in human crowds (i.e., social navigation) presents several challenges: The robot often needs to rely on its noisy sensors to identify and localize pedestrians in human crowds; the robot needs to plan efficient paths to reach its goals; the robot needs to do so in a safe and socially appropriate manner. Recent [...]
Design Iteration of Dexterous Compliant Robotic Manipulators
Abstract: The goal of personal robotics is to have robots in homes performing everyday tasks efficiently to improve our quality of life. Towards this end, manipulators are needed which are low cost, safe around humans, and approach human-level dexterity. However, existing off-the-shelf manipulators are expensive both in cost and manufacturing time, difficult to repair, and [...]
Continual Learning of Compositional Skills for Robust Robot Manipulation
Abstract: Real world robots need to continuously learn new manipulation tasks in a lifelong learning manner. These new tasks often share many sub-structures e.g. sub-tasks, controllers, preconditions, with previously learned tasks. To utilize these shared sub-structures, we explore a compositional and object-centric approach to learn manipulation tasks. The first part of this thesis focuses on [...]
Watch, Practice, Improve: Towards In-the-wild Manipulation
Abstract: The longstanding dream of many roboticists is to see robots perform diverse tasks in diverse environments. To build such a robot that can operate anywhere, many methods train on robotic interaction data. While these approaches have led to significant advances, they rely on heavily engineered setups or high amounts of supervision, neither of which [...]
Improving the Transparency of Agent Decision Making to Humans Using Demonstrations
Abstract: For intelligent agents (e.g. robots) to be seamlessly integrated into human society, humans must be able to understand their decision making. For example, the decision making of autonomous cars must be clear to the engineers certifying their safety, passengers riding them, and nearby drivers negotiating the road simultaneously. As an agent's decision making depends [...]
Perception amidst interaction: spatial AI with vision and touch for robot manipulation
Abstract: Robots currently lack the cognition to replicate even a fraction of the tasks humans do, a trend summarized by Moravec's Paradox. Humans effortlessly combine their senses for everyday interactions—we can rummage through our pockets in search of our keys, and deftly insert them to unlock our front door. Before robots can demonstrate such dexterity, [...]
Sparse-view 3D in the Wild
Abstract: Reconstructing 3D scenes and objects from images alone has been a long-standing goal in computer vision. We have seen tremendous progress in recent years, capable of producing near photo-realistic renderings from any viewpoint. However, existing approaches generally rely on a large number of input images (typically 50-100) to compute camera poses and ensure view [...]
Offline Learning for Stochastic Multi-Agent Planning in Autonomous Driving
Abstract: Fully autonomous vehicles have the potential to greatly reduce vehicular accidents and revolutionize how people travel and how we transport goods. Many of the major challenges for autonomous driving systems emerge from the numerous traffic situations that require complex interactions with other agents. For the foreseeable future, autonomous vehicles will have to share the [...]
Improving Robot Capabilities Through Reconfigurability
Abstract: Advancements in robot capabilities are often achieved through integrating more hardware components. These hardware additions often lead to systems with high power consumption, fragility, and difficulties in control and maintenance. However, is this approach the only path to enhancing robot functionality? In this talk, I introduce the PuzzleBots, a modular multi-robot system with passive [...]
Carnegie Mellon University
Spectral Mapping using Simple Sensors
Abstract: Spectral mapping holds significant importance in many exploration endeavors as it facilitates a deeper comprehension of material composition within a surveyed area. While imaging spectrometers excel in recording reflectance spectra into spectral maps, their large physical footprint, substantial power requirements, and operational intricacies render them unsuitable for integration into small rovers or resource-constrained missions. [...]
Causal Robot Learning for Manipulation
Abstract: Two decades into the third age of AI, the rise of deep learning has yielded two seemingly disparate realities. In one, massive accomplishments have been achieved in deep reinforcement learning, protein folding, and large language models. Yet, in the other, the promises of deep learning to empower robots that operate robustly in real-world environments [...]