Student Talks
Differentiable Collision Detection
Abstract: Collision detection between objects is critical for simulation, control, and learning for robotic systems. However, existing collision detection routines are inherently non-differentiable, limiting their applications in gradient-based optimization tools. In this talk, I present DCOL: a fast and fully differentiable collision-detection framework that reasons about collisions between a set of composable and highly expressive [...]
On Interaction, Imitation, and Causation
Abstract: A standard critique of machine learning models (especially neural networks) is that they pick up on spurious correlations rather than causal relationships and are therefore brittle in the face of distribution shift. Solving this problem in full generality is impossible (i.e. there might be no good way to distinguish between the two). However, if [...]
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 [...]
Carnegie Mellon University
Accelerating Numerical Methods for Optimal Control
Abstract: 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 [...]
Tactile SLAM: perception for dexterity via vision-based touch
Abstract: Touch provides a direct window into robot-object interaction, free from occlusion and aliasing faced by visual sensing. Collated tactile perception can facilitate contact-rich tasks---like in-hand manipulation, sliding, and grasping. Here, online estimates of object geometry and pose are crucial for downstream planning and control. With significant advances in tactile sensing, like vision-based touch, a [...]
Resource Allocation for Learning in Robotics
Abstract: Robots operating in the real world need fast and intelligent decision making systems. While these systems have traditionally consisted of human-engineered behaviors and world models, there has been a lot of interest in integrating them with data-driven components to achieve faster execution and reduce hand-engineering. Unfortunately, these learning-based methods require large amounts of training [...]
Planning with Dynamics by Interleaving Search and Trajectory Optimization
Abstract: Search-based planning algorithms enable autonomous agents like robots to come up with well-reasoned long-horizon plans to achieve a given task objective. They do so by searching over the graph that results from discretizing the state and action space. However, in robotics, several dynamically rich tasks require high-dimensional planning in the continuous space. For such [...]
Solving Constraint Tasks with Memory-Based Learning
Abstract: In constraint tasks, the current task state heavily limits what actions are available to an agent. Mechanical constraints exist in many common tasks such as construction, disassembly, and rearrangement and task space constraints exist in an even broader range of tasks. Deep reinforcement learning algorithms have typically struggled with constraint tasks for two main [...]
Head-Worn Assistive Teleoperation of Mobile Manipulators
Abstract: Mobile manipulators in the home can provide increased autonomy to individuals with severe motor impairments, who often cannot complete activities of daily living (ADLs) without the help of a caregiver. Teleoperation of an assistive mobile manipulator could enable an individual with motor impairments to independently perform self-care and household tasks, yet limited motor function [...]
Text Classification with Class Descriptions Only
Abstract: In this work, we introduce KeyClass, a weakly-supervised text classification framework that learns from class-label descriptions only, without the need to use any human-labeled documents. It leverages the linguistic domain knowledge stored within pre-trained language models and data programming to automatically label documents. We demonstrate its efficacy and flexibility by comparing it to state-of-the-art [...]
Multi-Object Tracking in the Crowd
Abstract: In this talk, I will focus on the problem of multi-object tracking in crowded scenes. Tracking within crowds is particularly challenging due to heavy occlusion and frequent crossover between tracking targets. The problem becomes more difficult when we only have noisy bounding boxes due to background and neighboring objects. Existing tracking methods try to [...]
Utilizing Panoptic Segmentation and a Locally-Conditioned Neural Representation to Build Richer 3D Maps
Abstract: Advances in deep-learning based perception and maturation of volumetric RGB-D mapping algorithms have allowed autonomous robots to be deployed in increasingly complex environments. For robust operation in open-world conditions however, perceptual capabilities are still lacking. Limitations of commodity depth sensors mean that complex geometries and textures cannot be reconstructed accurately. Semantic understanding is still [...]
Magnification-invariant retinal distance estimation using a laser aiming beam
Abstract: Retinal surgery procedures like epiretinal membrane peeling and retinal vein cannulation require surgeons to manipulate very delicate structures in the eye with little room for error. Many robotic surgery systems have been developed to help surgeons and enforce safeguards during these demanding procedures. One essential piece of information that is required to create and [...]
Bridging Humans and Generative Models
Abstract: Deep generative models make visual content creation more accessible to novice and professional users alike by automating the synthesis of diverse, realistic content based on a collected dataset. People often use generative models as data-driven sources, making it challenging to personalize a model easily. Currently, personalizing a model requires careful data curation, which is [...]
Impulse considerations for reasoning about intermittent contacts
Abstract: Many of our interactions with the environment involve making and breaking contacts. However, it is not always obvious how one should reason about these intermittent contacts (sequence, timings, locations) in an online and adaptive way. This is particularly relevant in gait generation for legged locomotion control, where it is standard to simply predefine and [...]
Multi-Human 3D Reconstruction from Monocular RGB Videos
Abstract: We study the problem of multi-human 3D reconstruction from RGB videos captured in the wild. Humans have dynamic motion, and reconstructing them in arbitrary settings is key to building 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 [...]
Learning and Translating Temporal Abstractions across Humans and Robots
Abstract: Humans possess a remarkable ability to learn to perform tasks from a variety of different sources-from language, instructions, demonstration, etc. In each case, they are able to easily extract the high-level strategy to solve the task, such as the recipe of cooking a dish, whilst ignoring irrelevant details, such as the precise shape of [...]
Robust Incremental Smoothing and Mapping
Abstract: In this work we present a method for robust optimization for online incremental Simultaneous Localization and Mapping (SLAM). Due to the NP-Hardness of data association in the presence of perceptual aliasing, tractable (approximate) approaches to data association will produce erroneous measurements. We require SLAM back-ends that can converge to accurate solutions in the presence [...]
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 [...]
Learning Parameter-Efficient Quadrotor Dynamics Models
Abstract: Operation of quadrotors through high-speed, high-acceleration maneuvers remains a challenging problem due to the complex aerodynamics in this regime. While standard physical models suffice for control in near-hover conditions, the primary challenge in executing aggressive trajectories is obtaining a model for the quadrotor dynamics that adequately models the aerodynamic effects present, including lift, drag, [...]
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 [...]
Predicting The Future and Linking the Past: Learning and Constructing Structured Models for Robotic Manipulation
Abstract: Intelligent robotic agents need to reason about the dynamics of their surrounding world, and use such dynamics reasoning to make future predictions for efficient task planning. In addition, it is also desirable for robots to associate past experience in their memories to their current observation, and conduct analogical reasoning to complete tasks at their [...]
Carnegie Mellon University
MSR Thesis Talk: Tushar Kusnur
Title: Search-based Planning for Sensor-based Coverage Abstract: Robots are excellent candidates for the dull, dirty, and dangerous jobs we do not want humans to perform. Today, these include inspection of large areas or structures, post-disaster assessment, and surveillance. Assessing the aftermath of the recent Fern Hollow bridge collapse in Pittsburgh is one such example. Many [...]
Human-in-the-loop Model Creation
Abstract: Deep generative models make visual content creation more accessible to novice users by automating the synthesis of diverse, realistic content based on a collected dataset. However, the current machine learning approaches miss several elements of the creative process -- the ability to synthesize things that go far beyond the data distribution and everyday experience, [...]
Robotic Interestingness via Human-Informed Few-Shot Object Detection
Abstract: Interestingness recognition is crucial for decision making in autonomous exploration for mobile robots. Previous methods proposed an unsupervised online learning approach that can adapt to environments and detect interesting scenes quickly, but lack the ability to adapt to human-informed interesting objects. To solve this problem, we introduce a human-interactive framework, AirInteraction, that can detect [...]
Carnegie Mellon University
MSR Thesis Talk: Nikhil Angad Bakshi
Title: See But Don't Be Seen: Towards Stealthy Active Search in Heterogeneous Multi-Robot Systems Abstract: Robotic solutions for quick disaster response are essential to ensure minimal loss of life, especially when the search area is too dangerous or too vast for human rescuers. We model this problem as an asynchronous multi-agent active-search task where each robot aims [...]
Carnegie Mellon University
MSR Thesis Talk: Yves Georgy Daoud
Title: Spatial Tasking in Human-Robot Collaborative Exploration Abstract: This work develops a methodology for collaborative human-robot exploration that leverages implicit coordination. Most autonomous single- and multi-robot exploration systems require a remote operator to provide explicit guidance to the robot team. Few works consider how to integrate the human partner alongside robots to provide guidance in the [...]
Carnegie Mellon University
MSR Thesis Talk: Ambareesh Revanur
Title: Towards Video-based Physiology Estimation Abstract: RGB-video based human physiology estimation has a wide range of practical applications in telehealth, sports and deep fake detection. Therefore, researchers in the community have collected several video datasets and have advanced new methods over the years. In this dissertation, we study these methods extensively and aim to address the [...]
Carnegie Mellon University
MSR Thesis Talk: Raghavv Goel
Title: Automating Ultrasound Based Vascular Access Abstract: Timely care of trauma patients is important to prevent casualties in resource-limited regions such as the battlefield. In order to treat such trauma using point of care diagnosis, medical practitioners typically use an ultrasound for vascular access or detection of subcutaneous splinters for providing critical care. The problem here is two-fold: [...]
Carnegie Mellon University
MSR Thesis Talk: Mayank Singh
Title: Analogical Networks: Memory-Modulated In-Context 3D Parsing Abstract: Recent advances in the applications of deep neural networks to numerous visual perception tasks have shown excellent performance. However, this generally requires access to large amount of training samples and hence one persistent challenge is the setting of few-shot learning. In most existing works, a separate parametric neural [...]
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 [...]
Carnegie Mellon University
MSR Thesis Talk: Yutian Lei
Title: ARC: AdveRsarial Calibration between Modalities Abstract: Advances in computer vision and machine learning techniques have led to flourishing success in RGB-input perception tasks, which has also opened unbounded possibilities for non-RGB-input perception tasks, such as object detection from wireless signals, point clouds, and infrared light. However, compared to the matured development pipeline of RGB-input [...]
FRIDA: Supporting Artistic Communication in Real-World Image Synthesis Through Diverse Input Modalities
Abstract: FRIDA, a Framework and Robotics Initiative for Developing Arts, is a robot painting system designed to translate an artist's high-level intentions into real world paintings. FRIDA can paint from combinations of input images, text, style examples, sounds, and sketches. Planning is performed in a differentiable, simulated environment created using real data from the robot [...]
Perception for High-Speed Off-Road Driving
Abstract: On-road autonomous driving has seen rapid progress in recent years with driverless vehicles being tested in various cities worldwide. However, this progress is limited to cities with well-established infrastructure and has yet to transfer to off-road regimes with unstructured environments and few paved roads. Advances in high-speed and reliable autonomous off-road driving can unlock [...]
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 sub-structures (in the form of sub-tasks, controllers) with previously learned tasks. To utilize these shared sub-structures, we explore a compositional and object-centric approach to learn manipulation tasks. While compositionality in robot manipulation can manifest [...]
Carnegie Mellon University
MSR Thesis Talk: Samuel Ong
Title: Data-Driven Slip Model for Improved Localization and Path Following applied to Lunar Micro-Rovers Abstract Micro-lunar rovers need to solve a slew of challenges on the Moon, with no human intervention. One such challenge is the need to know their location in order to navigate and build maps. However, localization is challenging on the moon due [...]
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 [...]
Robust and Context-Aware Real-Time Collaborative Robot Handling with Dynamic Gesture Commands
Abstract: Real-time collaborative robot (cobot) handling is a task where the cobot maneuvers an object under human dynamic gesture commands. Enabling dynamic gesture commands is useful when the human needs to avoid direct contact with the robot or the object handled by the robot. However, the key challenge lies in the heterogeneity in human behaviors [...]
Equivalent Policy Sets for Learning Aligned Models and Abstractions
Abstract: Recent successes in model-based reinforcement learning (MBRL) have demonstrated the enormous value that learned representations of environmental dynamics (i.e., models) can impart to autonomous decision making. While a learned model can never perfectly represent the dynamics of complex environments, models that are accurate in the "right” ways may still be highly useful for decision [...]
Dynamic Route Guidance in Vehicle Networks by Simulating Future Traffic Patterns
Abstract: Roadway congestion leads to wasted time and money and environmental damage. Since adding more roadway capacity is often not possible in urban environments, it is becoming more important to use existing road networks more efficiently. Toward this goal, recent research in real-time, schedule-driven intersection control has shown an ability to significantly reduce the delays [...]
Adaptive Robotic Assistance through Observations of Human Behavior
Abstract: Assistive robots should take actions that support people's goals. This is especially true as robots enter into environments where personal agency is paramount, such as a person's home. Home environments have a wide variety of "optimal' solutions that depend on personal preference, making it difficult for a robot to know the goal it should [...]
Beyond Pick-and-Place: Towards Dynamic and Contact-rich Motor Skills with Reinforcement Learning
Abstract: Interactions with the physical world are at the core of robotics. However, robotics research, especially in manipulation, has been mainly focused on tasks with limited interactions with the physical world such as pick-and-place or pushing objects on the table top. These interactions are often quasi-static, have predefined or limited sequence of contact events and [...]
Adaptive-Anytime Planning and Mapping for Multi-Robot Exploration in Large Environments
Abstract: Robotic systems are being leveraged to explore environments too hazardous for humans to enter. Robot sensing, compute, and kinodynamic (SCK) capabilities are inextricably tied to the size, weight, and power (SWaP) constraints of the vehicle. When designing a robot team for exploration, the diversity and types of robots used must be carefully considered because [...]
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 [...]
Enabling Data-Efficient Real-World Model-Based Manipulation by Estimating Preconditions for Inaccurate Models
Abstract: This thesis explores estimating and reasoning about model deviation in robot learning for manipulation to improve data efficiency and reliability to enable real-robot manipulation in a world where models are inaccurate but still useful. Existing strategies are presented for improving planning robustness with low amounts of real-world data by an empirically estimated model precondition to guide [...]
Robust Adaptive Reinforcement Learning for Safety Critical Applications via Curricular Learning
Abstract: Reinforcement Learning (RL) presents great promises for autonomous agents. However, when using robots in a safety critical domain, a system has to be robust enough to be deployed in real life. For example, the robot should be able to perform across different scenarios it will encounter. The robot should avoid entering undesirable and irreversible [...]
MSR Thesis Talk: Yichen Li
Title: Simulation-guided Design for Vision-based Tactile Sensing on a Soft Robot Finger Abstract: Soft pneumatic robot manipulators have garnered widespread interest due to their compliance and flexibility, which enable soft, non-destructive grasping and strong adaptability to complex working environments. Tactile sensing is crucial for these manipulators to provide real-time contact information for control and manipulation. [...]
Controllable Visual-Tactile Synthesis
Abstract: Deep generative models have various content creation applications such as graphic design, e-commerce, and virtual Try-on. However, current works mainly focus on synthesizing realistic visual outputs, often ignoring other sensory modalities, such as touch, which limits physical interaction with users. The main challenges for multi-modal synthesis lie in the significant scale discrepancy between vision [...]
Perceiving Particles Inside a Container using Dynamic Touch Sensing
Abstract: Dynamic touch sensing has shown potential for multiple tasks. In this talk, I will present how we utilize dynamic touch sensing to perceive particles inside a container with two tasks: classification of the particles inside a container and property estimation of the particles inside a container. First, we try to recognize what is inside [...]
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 on building drivable realistic face avatars, but they rarely include [...]
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 [...]
Examining the Role of Adaptation in Human-Robot Collaboration
Abstract: Human and AI partners increasingly need to work together to perform tasks as a team. In order to act effectively as teammates, collaborative AI should reason about how their behaviors interplay with the strategies and skills of human team members as they coordinate on achieving joint goals. This talk will discuss a formalism for [...]
A Multi-view Synthetic and Real-world Human Activity Recognition Dataset
Abstract: Advancements in Human Activity Recognition (HAR) partially relies on the creation of datasets that cover a broad range of activities under various conditions. Unfortunately, obtaining and labeling datasets containing human activity is complex, laborious, and costly. One way to mitigate these difficulties with sufficient generality to provide robust activity recognition on unseen data is [...]
Eye Gaze for Intelligent Driving
Abstract: Intelligent vehicles have been proposed as one path to increasing vehicular safety and reduce on-road crashes. Driving intelligence has taken many forms, ranging from simple blind spot occupancy or forward collision warnings to lane keeping and all the way to full driving autonomy in certain situations. Primarily, these methods are outward-facing and operate on [...]
Dense 3D Representation Learning for Geometric Reasoning in Manipulation Tasks
Abstract: When solving a manipulation task like "put away the groceries" in real environments, robots must understand what *can* happen in these environments, as well as what *should* happen in order to accomplish the task. This knowledge can enable downstream robot policies to directly reason about which actions they should execute, and rule out behaviors [...]
Passive Coupling in Robot Swarms
Abstract: In unstructured environments, ant colonies demonstrate remarkable abilities to adaptively form functional structures in response to various obstacles, such as stairs, gaps, and holes. Drawing inspiration from these creatures, robot swarms can collectively exhibit complex behaviors and achieve tasks that individual robots cannot accomplish. Existing modular robot platforms that employ dynamic coupling and decoupling [...]
Learning novel objects during robot exploration via human-informed few-shot detection
Abstract: Autonomous mobile robots exploring in unfamiliar environments often need to detect target objects during exploration. Most prevalent approach is to use conventional object detection models, by training the object detector on large abundant image-annotation dataset, with a fixed and predefined categories of objects, and in advance of robot deployment. However, it lacks the capability [...]
Learning to Perceive and Predict Everyday Interactions
Abstract: This thesis aims to develop a computer vision system that can understand everyday human interactions with rich spatial information. Such systems can benefit VR/AR to perceive the reality and modify its virtual twin, and robotics to learn manipulation by watching human. Previous methods have been limited to constrained lab environment or pre-selected objects with [...]
Learning Models and Cost Functions from Unlabeled Data for Off-Road Driving
Abstract: Off-road driving is an important instance of navigation in unstructured environments, which is a key robotics problem with many applications, such as exploration, agriculture, disaster response and defense. The key challenge in off-road driving is to be able to take in high dimensional, multi-modal sensing data and use it to make intelligent decisions on [...]
Active Vision for Manipulation
Abstract: Decades of research on computer vision has highlighted the importance of active sensing -- where the agent actively controls parameters of the sensor to improve perception. Research on active perception the context of robotic manipulation has demonstrated many novel and robust sensing strategies involving a multitude of sensors like RGB and RGBD cameras, a [...]