/
index.json
1 lines (1 loc) · 15 KB
/
index.json
1
[{"authors":["admin"],"categories":null,"content":"As of fall 2020, I am a PhD student in the Robotics Institute at Carnegie Mellon University advised by Prof. Changliu Liu and Prof. Andrea Bajcsy. I am grateful to be funded by the NSF Graduate Research Fellowship.\nPreviously, I was a data scientist at the Global AI Accelerator (GAIA) within Ericsson.\nAs an undergrad at Berkeley, I primarily worked with Prof. Anca Dragan, but I also had the privilege of working in Prof. Ruzena Bajcsy's and Prof. Ron Fearing's labs.\nPlease see my Google Scholar for an up-to-date list of publications.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"2525497d367e79493fd32b198b28f040","permalink":"/authors/admin/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/authors/admin/","section":"authors","summary":"As of fall 2020, I am a PhD student in the Robotics Institute at Carnegie Mellon University advised by Prof. Changliu Liu and Prof. Andrea Bajcsy. I am grateful to be funded by the NSF Graduate Research Fellowship.\nPreviously, I was a data scientist at the Global AI Accelerator (GAIA) within Ericsson.\nAs an undergrad at Berkeley, I primarily worked with Prof. Anca Dragan, but I also had the privilege of working in Prof.","tags":null,"title":"Ravi Pandya","type":"authors"},{"authors":["T. Wei","L. Ma","**Ravi Pandya**","C. Liu"],"categories":[],"content":"","date":1695859200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1695859200,"objectID":"dda7ea37cbf1b8c8761fa7f73719e090","permalink":"/publication/lcss-robust/","publishdate":"2019-12-31T10:05:27-08:00","relpermalink":"/publication/lcss-robust/","section":"publication","summary":"We introduce a least-conservative robust safe controller for dynamical systems with additive and multiplicative multimodal uncertainty for CBF-like safe control methods. We test our method on a simulated segway robot and find it is less conservative than existing unimodal robust control methods.","tags":[],"title":"Robust Safe Control with Multi-Modal Uncertainty","type":"publication"},{"authors":["**Ravi Pandya***","M. Zhao*","C. Liu","R. Simmons","H. Admoni"],"categories":[],"content":"","date":1694736000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1694736000,"objectID":"27280c944e480062aca9525f736f3d4e","permalink":"/publication/icra-multiagent/","publishdate":"2019-12-31T10:05:27-08:00","relpermalink":"/publication/icra-multiagent/","section":"publication","summary":"We introduce a novel method for generating explanations of collaborative strategies for humans and robots in tasks with multiple Nash equilibria. We generate a visual state-based explanation of what each agent should do in an upcoming collaboration. Ultimately, we find that our explanations help real participants better explore the full space of strategies and collaborate with autonomous partners more quickly.","tags":[],"title":"Multi-Agent Strategy Explanations for Human-Robot Collaboration","type":"publication"},{"authors":["**Ravi Pandya***","Z. Wang*","Y. Nakahira","C. Liu"],"categories":[],"content":"","date":1694563200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1694563200,"objectID":"39670487bfeaaecc705deaf4a6831210","permalink":"/publication/icra-towards-safe/","publishdate":"2019-12-31T10:05:27-08:00","relpermalink":"/publication/icra-towards-safe/","section":"publication","summary":"We formulate a novel modification to typical human intention prediction via Bayesian inference that accounts for the influence that the robot will have on the person. Using this conditional behavior prediction model, the robot can proactively influence a human collaborator to choose efficient actions for the task. We find in a user study that participants tend to enjoy collaborating with this algorithm over baselines.","tags":[],"title":"Towards Proactive Safe Human-Robot Collaborations via Data-Efficient Conditional Behavior Prediction","type":"publication"},{"authors":["**Ravi Pandya**","T. Wei","C. Liu"],"categories":[],"content":"","date":1692921600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1692921600,"objectID":"3f531fdcdeddd409fa6473622d196726","permalink":"/publication/acc-multimodal/","publishdate":"2019-12-31T10:05:27-08:00","relpermalink":"/publication/acc-multimodal/","section":"publication","summary":"We derive a least-conservative robust safe controller for dynamical systems with additive multimodal uncertainty (where additive refers to how the uncertainty enters into the dynamics with respect to the control input). We test our controller on a simulated human-robot system where the robot is uncertain of the human's goal and find this approach to be safer than existing maximum-likelihood-based unimodal robust controllers.","tags":[],"title":"Multimodal Safe Control for Human-Robot Interaction","type":"publication"},{"authors":[],"categories":null,"content":"","date":1667257200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1667257200,"objectID":"aa80f547717b9acc3227304395a18d17","permalink":"/talk/iros-safe/","publishdate":"2019-12-31T10:32:57-08:00","relpermalink":"/talk/iros-safe/","section":"talk","summary":"IROS 2022 Paper Presentation","tags":[],"title":"Safe and Efficient Efficient Exploration of Human Models During Human-Robot Interaction","type":"talk"},{"authors":["**Ravi Pandya**","C. Liu"],"categories":[],"content":"","date":1667174400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1667174400,"objectID":"b2517cc00c28284f03103beb4744dea2","permalink":"/publication/iros-safe/","publishdate":"2019-12-31T10:05:27-08:00","relpermalink":"/publication/iros-safe/","section":"publication","summary":"We study the problem of adapting a robot's dynamics model of a human collaborator online while staying safe; we test out controllers with different risk preferences and measure how they are affected by the presence of safe control. Ultimately, we find that a risk-seeking control can learn a good model, but necessitates activating the safety controller more than other methods.","tags":[],"title":"Safe and Efficient Exploration of Human Models During Human-Robot Interaction","type":"publication"},{"authors":[],"categories":null,"content":"","date":1572649200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1572649200,"objectID":"b9941ff1971139f7f427161f17423bae","permalink":"/talk/corl-feedback/","publishdate":"2019-12-31T10:32:57-08:00","relpermalink":"/talk/corl-feedback/","section":"talk","summary":"CoRL 2019 Oral, Acceptance: **5.3%**","tags":[],"title":"Nonverbal Robot Feedback for Human Teachers","type":"talk"},{"authors":["**Ravi Pandya***","S.H. Huang\\*","I. Huang\\*","A.D. Dragan"],"categories":[],"content":"","date":1572393600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1572393600,"objectID":"e12da4c443bd361e642bdfee26f4ab2d","permalink":"/publication/corl-feedback/","publishdate":"2019-12-26T18:48:09-08:00","relpermalink":"/publication/corl-feedback/","section":"publication","summary":"We study the problem of enabling a robot learner to give nonverbal feedback to a human teacher. We focus on using gaze as a predictor of the human teacher's next action and find in simulation that this approach leads to faster and more accurate task learning. In both online and in-person user studies, we find that this nonverbal feedback also helps real human teachers get a better mental model of the robot learner and helps improve the robot's learning performance.","tags":[],"title":"Nonverbal Robot Feedback for Human Teachers","type":"publication"},{"authors":[],"categories":[],"content":"","date":1556668800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1556668800,"objectID":"0609212e6b051fb0aac83fe9989750a6","permalink":"/project/ee-192/","publishdate":"2019-05-01T00:00:00Z","relpermalink":"/project/ee-192/","section":"project","summary":"Designed circuits and PCBs for motor drivers, encoders, and a line camera; wrote sensing and controls code to autonomously navigate a complicated track.","tags":[],"title":"Line-Following Car","type":"project"},{"authors":[],"categories":[],"content":"","date":1556668800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1556668800,"objectID":"f8f4d30f468b27e92db8d3f55161a0a7","permalink":"/project/ee-222/","publishdate":"2019-05-01T00:00:00Z","relpermalink":"/project/ee-222/","section":"project","summary":"Analyzed the robustness of nonlinear controllers (Feedback Linearizing, Adaptive, Computed Torque, Sliding Mode) under disturbances and model misspecification for a 2DOF Matlab simulated robot arm and a 7DOF Kinova Jaco in a C++ ROS framework utilizing Gazebo.","tags":[],"title":"Robustness Analysis of Nonlinear Controllers","type":"project"},{"authors":["**Ravi Pandya**","S.H. Huang","D. Hadfield-Menell","A.D. Dragan"],"categories":[],"content":"","date":1548806400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1548806400,"objectID":"2ef96d06053e662d7c5410d4f6340343","permalink":"/publication/aies-bandits/","publishdate":"2019-12-30T17:42:28-08:00","relpermalink":"/publication/aies-bandits/","section":"publication","summary":"We study how an AI agent can assist a human by suggesting options in a multi-armed bandit problem when both agents are learning the reward from arms from scratch. We find in a user study that people have two main modes of selecting arms that can be distibguished by the entropy of the arm frequencies over time, and that participants matched with an assistant with similar entropy profiles will be most helpful to them.","tags":[],"title":"Human-AI Learning Performance in Multi-Armed Bandits","type":"publication"},{"authors":["A. Nagabandi","G. Yang","T. Asmar","**Ravi Pandya**","G. Kahn","S. Levine","R.S. Fearing"],"categories":[],"content":"","date":1540944000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1540944000,"objectID":"bc81c4b5e6953661ec3e6fbe59b83811","permalink":"/publication/iros-dynamics/","publishdate":"2019-12-31T10:05:27-08:00","relpermalink":"/publication/iros-dynamics/","section":"publication","summary":"We enable a small underactuated robot to learn how to walk on different terrains with a small amount of data collected in the real world by training a neural network dynamics model and running MPC over it to track trajectories. Importantly, the dynamics model takes in images of the environment to condition on, allowing the robot to learn different gaits for different terrains with just a single model.","tags":[],"title":"Learning Image-Conditioned Dynamics Models for Under-actuated Legged Millirobots","type":"publication"},{"authors":["A. Bestick","**Ravi Pandya**","R. Bajcsy","A.D. Dragan"],"categories":[],"content":"","date":1527724800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1527724800,"objectID":"c0c3a826036aa38083f1533ec2e2aac8","permalink":"/publication/icra-ergonomics/","publishdate":"2019-12-31T10:15:08-08:00","relpermalink":"/publication/icra-ergonomics/","section":"publication","summary":"We focus on understanding how to best learn ergonomic preferences from a human in object handovers, since each person will have individual comfort preferences or constraints. We study an active learning approach to learning a human ergonomic cost function compared to passive and random baselines, and find that while active learning estimates the human's cost function quickly, it incurs a higher ergonomic cost during learning.","tags":[],"title":"Learning Human Ergonomic Preferences for Handovers","type":"publication"},{"authors":[],"categories":[],"content":"","date":1514678400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1514678400,"objectID":"3f1fd4f98bbbb817f5b8b8b63b3dbd5a","permalink":"/project/ee-106a/","publishdate":"2017-12-31T00:00:00Z","relpermalink":"/project/ee-106a/","section":"project","summary":"Wrote software for sensing, planning and control of Baxter Robot to allow it to intelligently play a gameof checkers against a human.","tags":[],"title":"Checkers-Playing Robot","type":"project"},{"authors":null,"categories":null,"content":"[does listening to an audiobook count as reading? I say yes]\nBooks I\u0026rsquo;m currently reading Norwegian Wood - Haruki Murakami Books/Series I\u0026rsquo;ve read recently Between the World and Me - Ta-Nehisi Coates A Beautifully Foolish Endeavor - Hank Green Mistborn (The Final Empire, The Well of Ascension, The Hero of Ages) - Brandon Sanderson ","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"5bd3bdf927f7720b6c003276b4cf1995","permalink":"/books/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/books/","section":"","summary":"[does listening to an audiobook count as reading? I say yes]\nBooks I\u0026rsquo;m currently reading Norwegian Wood - Haruki Murakami Books/Series I\u0026rsquo;ve read recently Between the World and Me - Ta-Nehisi Coates A Beautifully Foolish Endeavor - Hank Green Mistborn (The Final Empire, The Well of Ascension, The Hero of Ages) - Brandon Sanderson ","tags":null,"title":"","type":"page"},{"authors":null,"categories":null,"content":"Follow Eevee on Instagram! ","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"bb5ef131cff791e87bdf3f0510421a8f","permalink":"/eevee/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/eevee/","section":"","summary":"Follow Eevee on Instagram! ","tags":null,"title":"","type":"page"},{"authors":null,"categories":null,"content":"Games I\u0026rsquo;ve played recently The Legend of Zelda: Tears of the Kingdon Super Mario Wonder Some Favorites The Legend of Zelda: Breath of the Wild Celeste Persona 5 Royal Super Mario Odyssey Donkey Kong Country: Tropical Freeze Pokemon Emerald Pokemon Black/White Super Mario Galaxy ","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"a879582cd427625a083bd04d7ae7a6e4","permalink":"/games/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/games/","section":"","summary":"Games I\u0026rsquo;ve played recently The Legend of Zelda: Tears of the Kingdon Super Mario Wonder Some Favorites The Legend of Zelda: Breath of the Wild Celeste Persona 5 Royal Super Mario Odyssey Donkey Kong Country: Tropical Freeze Pokemon Emerald Pokemon Black/White Super Mario Galaxy ","tags":null,"title":"","type":"page"},{"authors":null,"categories":null,"content":"Shows I\u0026rsquo;ve watched recently Jujutsu Kaisen Loki Some Favorites Mob Psycho 100 Avatar: The Last Airbender The Legend of Korra Breaking Bad Better Call Saul Fullmetal Alchemist: Brotherhood Terrace House Steins;gate ","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"ce1c0f094288b644e78c1548794f3174","permalink":"/shows/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/shows/","section":"","summary":"Shows I\u0026rsquo;ve watched recently Jujutsu Kaisen Loki Some Favorites Mob Psycho 100 Avatar: The Last Airbender The Legend of Korra Breaking Bad Better Call Saul Fullmetal Alchemist: Brotherhood Terrace House Steins;gate ","tags":null,"title":"","type":"page"}]