Search Results for author: Sehoon Ha

Found 28 papers, 5 papers with code

VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation

no code implementations6 Dec 2023 Naoki Yokoyama, Sehoon Ha, Dhruv Batra, Jiuguang Wang, Bernadette Bucher

Understanding how humans leverage semantic knowledge to navigate unfamiliar environments and decide where to explore next is pivotal for developing robots capable of human-like search behaviors.

Language Modelling Navigate

AAMDM: Accelerated Auto-regressive Motion Diffusion Model

no code implementations2 Dec 2023 Tianyu Li, Calvin Qiao, Guanqiao Ren, KangKang Yin, Sehoon Ha

This paper introduces the Accelerated Auto-regressive Motion Diffusion Model (AAMDM), a novel motion synthesis framework designed to achieve quality, diversity, and efficiency all together.

Denoising Motion Synthesis

BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuning

no code implementations16 Oct 2023 Tianle Huang, Nitish Sontakke, K. Niranjan Kumar, Irfan Essa, Stefanos Nikolaidis, Dennis W. Hong, Sehoon Ha

Domain randomization (DR), which entails training a policy with randomized dynamics, has proven to be a simple yet effective algorithm for reducing the gap between simulation and the real world.

Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanism

no code implementations24 Jun 2023 J. Taery Kim, Wenhao Yu, Yash Kothari, Jie Tan, Greg Turk, Sehoon Ha

To build a successful guide robot, our paper explores three key topics: (1) formalizing the navigation mechanism of a guide dog and a human, (2) developing a data-driven model of their interaction, and (3) improving user safety.

Learning and Adapting Agile Locomotion Skills by Transferring Experience

no code implementations19 Apr 2023 Laura Smith, J. Chase Kew, Tianyu Li, Linda Luu, Xue Bin Peng, Sehoon Ha, Jie Tan, Sergey Levine

Legged robots have enormous potential in their range of capabilities, from navigating unstructured terrains to high-speed running.

Reinforcement Learning (RL)

Residual Physics Learning and System Identification for Sim-to-real Transfer of Policies on Buoyancy Assisted Legged Robots

no code implementations16 Mar 2023 Nitish Sontakke, Hosik Chae, Sangjoon Lee, Tianle Huang, Dennis W. Hong, Sehoon Ha

In this work, we demonstrate robust sim-to-real transfer of control policies on the BALLU robots via system identification and our novel residual physics learning method, Environment Mimic (EnvMimic).

Learning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculum

no code implementations14 Mar 2023 Yunbo Zhang, Alexander Clegg, Sehoon Ha, Greg Turk, Yuting Ye

In-hand object manipulation is challenging to simulate due to complex contact dynamics, non-repetitive finger gaits, and the need to indirectly control unactuated objects.

Imitation Learning Object

Cascaded Compositional Residual Learning for Complex Interactive Behaviors

no code implementations17 Dec 2022 K. Niranjan Kumar, Irfan Essa, Sehoon Ha

Real-world autonomous missions often require rich interaction with nearby objects, such as doors or switches, along with effective navigation.

ViNL: Visual Navigation and Locomotion Over Obstacles

1 code implementation26 Oct 2022 Simar Kareer, Naoki Yokoyama, Dhruv Batra, Sehoon Ha, Joanne Truong

ViNL consists of: (1) a visual navigation policy that outputs linear and angular velocity commands that guides the robot to a goal coordinate in unfamiliar indoor environments; and (2) a visual locomotion policy that controls the robot's joints to avoid stepping on obstacles while following provided velocity commands.

Navigate Visual Navigation

Unified State Representation Learning under Data Augmentation

1 code implementation12 Sep 2022 Taylor Hearn, Sravan Jayanthi, Sehoon Ha

The capacity for rapid domain adaptation is important to increasing the applicability of reinforcement learning (RL) to real world problems.

Data Augmentation Domain Adaptation +2

Safe Reinforcement Learning for Legged Locomotion

no code implementations5 Mar 2022 Tsung-Yen Yang, Tingnan Zhang, Linda Luu, Sehoon Ha, Jie Tan, Wenhao Yu

In this paper, we propose a safe reinforcement learning framework that switches between a safe recovery policy that prevents the robot from entering unsafe states, and a learner policy that is optimized to complete the task.

reinforcement-learning Reinforcement Learning (RL) +1

Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning

no code implementations29 Sep 2021 Hao-Lun Hsu, Qiuhua Huang, Sehoon Ha

One of the key challenges to deep reinforcement learning (deep RL) is to ensure safety at both training and testing phases.

Continuous Control reinforcement-learning +1

PM-FSM: Policies Modulating Finite State Machine for Robust Quadrupedal Locomotion

no code implementations26 Sep 2021 Ren Liu, Nitish Sontakke, Sehoon Ha

Compared with the TGs, FSMs offer high-level management on each leg motion generator and enable a flexible state arrangement, which makes the learned behavior less vulnerable to unseen perturbations or challenging terrains.


Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge

no code implementations22 Sep 2021 Naoki Yokoyama, Qian Luo, Dhruv Batra, Sehoon Ha

Recent advances in deep reinforcement learning and scalable photorealistic simulation have led to increasingly mature embodied AI for various visual tasks, including navigation.

Benchmarking Image Augmentation +4

Success Weighted by Completion Time: A Dynamics-Aware Evaluation Criteria for Embodied Navigation

no code implementations14 Mar 2021 Naoki Yokoyama, Sehoon Ha, Dhruv Batra

Several related works on navigation have used Success weighted by Path Length (SPL) as the primary method of evaluating the path an agent makes to a goal location, but SPL is limited in its ability to properly evaluate agents with complex dynamics.


Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environments

no code implementations13 Mar 2021 Visak Kumar, Sehoon Ha, C. Karen Liu

An EAP takes as input the predicted future state error in the target environment, which is provided by an error-prediction function, simultaneously trained with the EAP.

Zero-shot Generalization

A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning

no code implementations6 Nov 2020 Qian Luo, Maks Sorokin, Sehoon Ha

Therefore, learning a navigation policy for a new robot with a new sensor configuration or a new target still remains a challenging problem.

Meta-Learning Visual Navigation

Observation Space Matters: Benchmark and Optimization Algorithm

no code implementations2 Nov 2020 Joanne Taery Kim, Sehoon Ha

Recent advances in deep reinforcement learning (deep RL) enable researchers to solve challenging control problems, from simulated environments to real-world robotic tasks.

Learning to be Safe: Deep RL with a Safety Critic

no code implementations27 Oct 2020 Krishnan Srinivasan, Benjamin Eysenbach, Sehoon Ha, Jie Tan, Chelsea Finn

Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself.

Reinforcement Learning (RL) Transfer Learning

Learning to Walk in the Real World with Minimal Human Effort

1 code implementation20 Feb 2020 Sehoon Ha, Peng Xu, Zhenyu Tan, Sergey Levine, Jie Tan

In this paper, we develop a system for learning legged locomotion policies with deep RL in the real world with minimal human effort.

Multi-Task Learning

Learning Fast Adaptation with Meta Strategy Optimization

1 code implementation28 Sep 2019 Wenhao Yu, Jie Tan, Yunfei Bai, Erwin Coumans, Sehoon Ha

The key idea behind MSO is to expose the same adaptation process, Strategy Optimization (SO), to both the training and testing phases.


Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation

no code implementations27 Sep 2019 Xinlei Pan, Tingnan Zhang, Brian Ichter, Aleksandra Faust, Jie Tan, Sehoon Ha

Here, we propose a zero-shot imitation learning approach for training a visual navigation policy on legged robots from human (third-person perspective) demonstrations, enabling high-quality navigation and cost-effective data collection.

Disentanglement Imitation Learning +1

Estimating Mass Distribution of Articulated Objects using Non-prehensile Manipulation

no code implementations9 Jul 2019 K. Niranjan Kumar, Irfan Essa, Sehoon Ha, C. Karen Liu

Using our method, we train a robotic arm to estimate the mass distribution of an object with moving parts (e. g. an articulated rigid body system) by pushing it on a surface with unknown friction properties.

Friction Object +1

Learning to Walk via Deep Reinforcement Learning

no code implementations26 Dec 2018 Tuomas Haarnoja, Sehoon Ha, Aurick Zhou, Jie Tan, George Tucker, Sergey Levine

In this paper, we propose a sample-efficient deep RL algorithm based on maximum entropy RL that requires minimal per-task tuning and only a modest number of trials to learn neural network policies.

reinforcement-learning Reinforcement Learning (RL)

Learning a Unified Control Policy for Safe Falling

no code implementations8 Mar 2017 Visak CV Kumar, Sehoon Ha, C. Karen Liu

With this mixture of actor-critic architecture, the discrete contact sequence planning is solved through the selection of the best critics while the continuous control problem is solved by the optimization of actors.

Continuous Control

Cannot find the paper you are looking for? You can Submit a new open access paper.