Paul G. Allen School Courses

Integrated Task and Motion Planning in Belief Space

Explore integrated strategies for planning, perception, and action in complex mobile manipulation domains using belief space planning and hierarchical goal regression.

• YouTube
• 1 hour 7 minutes
• Self-Paced
• Free Video

Deja Vu - The Story of Vision & AI

Explore the evolution of computer vision and AI with Ali Farhadi, covering deep neural networks, object detection, visual reasoning, and future predictions in this insightful seminar.

• YouTube
• 57 minutes
• Self-Paced
• Free Video

Probabilistic Models for Learning a Semantic Parser Lexicon

Probabilistic models for learning semantic parser lexicons from question/answer pairs, improving accuracy and efficiency without extensive human input or dataset-specific engineering.

• YouTube
• 42 minutes
• Self-Paced
• Free Video

Decision-Theoretic Planning to Control Crowdsourced Workflows

Explores decision-theoretic planning for optimizing crowdsourced workflows, covering POMDPs, dynamic workflow switching, taxonomy construction, and data annotation optimization for machine learning applications.

• YouTube
• 52 minutes
• Self-Paced
• Free Video

The Power of Gradients in Inverse Dynamics Problems - Tao Du, MIT

Exploring analytical gradients in physics simulation for computational design of dynamic systems, with applications in robotics, biomechanics, and computer graphics.

• YouTube
• 54 minutes
• Self-Paced
• Free Video

Dynamic Robot Manipulation - Learned Optimization, Deformable Materials, and the Cloud

Explore dynamic robot manipulation through integrated planning, deep learning, and cloud computing for high-speed, reliable motions in unstructured environments.

• YouTube
• 53 minutes
• Self-Paced
• Free Video

Perceptual Robot Learning - David Held, CMU

Explore innovative approaches to robot perception and planning for manipulating diverse objects, enhancing capabilities in cloth handling, articulated objects, and transparent materials.

• YouTube
• 57 minutes
• Self-Paced
• Free Video

Learning Robot Policies from Imperfect Teachers - Taylor Kessler Faulkner, UT Austin

Explore algorithms for robots learning from imperfect human teachers, addressing inattention and inaccurate information to enhance interactive Reinforcement Learning and improve human-robot teaching interactions.

• YouTube
• 53 minutes
• Self-Paced
• Free Video

Certifiable Outlier-Robust Geometric Perception - Robots that See through the Clutter with Confidence

Explore cutting-edge algorithms for robust geometric perception in robotics, enhancing safety and reliability in autonomous systems across various applications.

• YouTube
• 1 hour
• Self-Paced
• Free Video

Towards Generalization of Precise Robot Skills - Accurate Pick-and-Place of Novel Objects

Explore precise robotic generalization for pick-and-place tasks using simulation-learned models. Discover how visuo-tactile sensing enables accurate object manipulation and placement with sub-millimeter precision for novel items.

• YouTube
• 59 minutes
• Self-Paced
• Free Video

Better Ways to Measure and Move - Joint Optimization of Agent's Physical Design and Computational Reasoning

Explore joint optimization of physical design and computational reasoning for intelligent agents, enhancing sensor networks, legged robots, and soft robotics through machine learning techniques.

• YouTube
• 1 hour
• Self-Paced
• Free Video

Assistive Autonomy Revisited - Brenna Argall, Northwestern University

Exploring robotics autonomy to enhance human independence for those with motor impairments. Discusses challenges, research, and innovative approaches in assistive technology and rehabilitation robotics.

• YouTube
• 52 minutes
• Self-Paced
• Free Video

Robots That Talk and Learn - Shiwali Mohan, Palo Alto Research Center

Explore interactive task learning for robots, focusing on designing collaborative human-AI systems. Discover advances in enabling robots to learn new tasks through natural interactions with humans.

• YouTube
• 59 minutes
• Self-Paced
• Free Video

On the Complexity of Anonymous Communication Through Public Networks

Explores onion routing for anonymous online communication, presenting a novel protocol that achieves fault-tolerance, efficiency, and anonymity against active adversaries observing network traffic.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

More Communication Lower Bounds for Information-Theoretic MPC

Explores communication complexity lower bounds in information-theoretic secure multiparty computation, covering perfect passive and malicious security settings with various party thresholds and reactive functionalities.

• YouTube
• 22 minutes
• Self-Paced
• Free Video