no code implementations • 9 Mar 2024 • Ruiqi Ni, Ahmed H. Qureshi
Constrained Motion Planning (CMP) aims to find a collision-free path between the given start and goal configurations on the kinematic constraint manifolds.
no code implementations • 9 Sep 2023 • Zixing Wang, Ahmed H. Qureshi
Anytime 3D human pose forecasting is crucial to synchronous real-world human-machine interaction, where the term ``anytime" corresponds to predicting human pose at any real-valued time step.
no code implementations • 5 Sep 2023 • Manav Kulshrestha, Ahmed H. Qureshi
Robotic manipulation tasks, such as object rearrangement, play a crucial role in enabling robots to interact with complex and arbitrary environments.
no code implementations • 26 Jun 2023 • Vidyaa Krishnan Nivash, Ahmed H. Qureshi
These encodings along with agents' local information, are passed through an encoder to obtain time-dependent latent variables for a motion policy predicting the future trajectories.
no code implementations • 10 Jun 2023 • Vivek Gupta, Praphpreet Dhir, Jeegn Dani, Ahmed H. Qureshi
Object rearrangement is a fundamental problem in robotics with various practical applications ranging from managing warehouses to cleaning and organizing home kitchens.
1 code implementation • 1 Jun 2023 • Ruiqi Ni, Ahmed H. Qureshi
Neural motion planners (NMPs) demonstrate fast computational speed in finding path solutions but require a huge amount of expert trajectories for learning, thus adding a significant training computational load.
1 code implementation • 14 Mar 2023 • Daniel Lawson, Ahmed H. Qureshi
Recent work has shown the promise of creating generalist, transformer-based, models for language, vision, and sequential decision-making problems.
no code implementations • 2 Mar 2023 • Zikang Xiong, Daniel Lawson, Joe Eappen, Ahmed H. Qureshi, Suresh Jagannathan
Synthesizing planning and control policies in robotics is a fundamental task, further complicated by factors such as complex logic specifications and high-dimensional robot dynamics.
Hierarchical Reinforcement Learning reinforcement-learning +2
no code implementations • 11 Nov 2022 • Daniel Lawson, Ahmed H. Qureshi
We show that Control Transformer can successfully navigate through mazes and transfer to unknown environments.
no code implementations • 6 Oct 2022 • Abhinav K. Keshari, Hanwen Ren, Ahmed H. Qureshi
Furthermore, our user study with 10 independent participants indicated our approach enables a safe, natural, and socially-aware human-robot objects' co-grasping experience compared to a standard robot grasping technique.
1 code implementation • 30 Sep 2022 • Ruiqi Ni, Ahmed H. Qureshi
We evaluate our method in various cluttered 3D environments, including the Gibson dataset, and demonstrate its ability to solve motion planning problems for 4-DOF and 6-DOF robot manipulators where the traditional grid-based Eikonal planners often face the curse of dimensionality.
no code implementations • 23 Aug 2022 • Hanwen Ren, Ahmed H. Qureshi
Active sensing and planning in unknown, cluttered environments is an open challenge for robots intending to provide home service, search and rescue, narrow-passage inspection, and medical assistance.
no code implementations • 21 May 2022 • Zhiquan Wang, Bedrich Benes, Ahmed H. Qureshi, Christos Mousas
The agent is then randomly modified within the allowed ranges creating a new generation of several hundred agents.
1 code implementation • 2 Mar 2022 • Zikang Xiong, Joe Eappen, Ahmed H. Qureshi, Suresh Jagannathan
Model-free Deep Reinforcement Learning (DRL) controllers have demonstrated promising results on various challenging non-linear control tasks.
1 code implementation • 5 Jun 2021 • Jacob J. Johnson, Uday S. Kalra, Ankit Bhatia, Linjun Li, Ahmed H. Qureshi, Michael C. Yip
A popular technique to improve the efficiency of these planners is to restrict search space in the planning domain.
no code implementations • 2 Jun 2021 • Ahmed H. Qureshi, Arsalan Mousavian, Chris Paxton, Michael C. Yip, Dieter Fox
We propose NeRP (Neural Rearrangement Planning), a deep learning based approach for multi-step neural object rearrangement planning which works with never-before-seen objects, that is trained on simulation data, and generalizes to the real world.
1 code implementation • 17 Jan 2021 • Linjun Li, Yinglong Miao, Ahmed H. Qureshi, Michael C. Yip
Kinodynamic Motion Planning (KMP) is to find a robot motion subject to concurrent kinematics and dynamics constraints.
no code implementations • 17 Oct 2020 • Ahmed H. Qureshi, Jiangeng Dong, Asfiya Baig, Michael C. Yip
However, few solutions to constrained motion planning are available, and those that exist struggle with high computational time complexity in finding a path solution on the manifolds.
no code implementations • 9 Aug 2020 • Ahmed H. Qureshi, Jiangeng Dong, Austin Choe, Michael C. Yip
The presence of task constraints imposes a significant challenge to motion planning.
1 code implementation • 13 Jul 2019 • Ahmed H. Qureshi, Yinglong Miao, Anthony Simeonov, Michael C. Yip
We validate MPNet against gold-standard and state-of-the-art planning methods in a variety of problems from 2D to 7D robot configuration spaces in challenging and cluttered environments, with results showing significant and consistently stronger performance metrics, and motivating neural planning in general as a modern strategy for solving motion planning problems efficiently.
no code implementations • ICLR 2020 • Ahmed H. Qureshi, Jacob J. Johnson, Yuzhe Qin, Taylor Henderson, Byron Boots, Michael C. Yip
The composition of elementary behaviors to solve challenging transfer learning problems is one of the key elements in building intelligent machines.
1 code implementation • 25 Apr 2019 • Mayur J. Bency, Ahmed H. Qureshi, Michael C. Yip
In this work, we introduce a novel way of producing fast and optimal motion plans for static environments by using a stepping neural network approach, called OracleNet.
1 code implementation • 26 Sep 2018 • Ahmed H. Qureshi, Michael C. Yip
In this paper, we present a neural network-based adaptive sampler for motion planning called Deep Sampling-based Motion Planner (DeepSMP).
no code implementations • ICLR 2019 • Ahmed H. Qureshi, Byron Boots, Michael C. Yip
We consider a problem of learning the reward and policy from expert examples under unknown dynamics.
no code implementations • 22 Jul 2018 • Zaid Tahir, Ahmed H. Qureshi, Yasar Ayaz, Raheel Nawaz
The proposed algorithms greatly improve the convergence rate and have a more efficient memory utilization.
1 code implementation • 14 Jun 2018 • Ahmed H. Qureshi, Anthony Simeonov, Mayur J. Bency, Michael C. Yip
Fast and efficient motion planning algorithms are crucial for many state-of-the-art robotics applications such as self-driving cars.