46 citations · 98 across the 11 of their papers we have counts for
11 papers
Neural USD: An object-centric framework for iterative editing and control
Alejandro Escontrela, Shrinu Kushagra, Sjoerd van Steenkiste +5
Amazing progress has been made in controllable generative modeling, especially over the last few years. However, some challenges remain. One of them is precise and iterative object…
GaussGym: An open-source real-to-sim framework for learning locomotion from pixels
Alejandro Escontrela, Justin Kerr, Arthur Allshire +4
We present a novel approach for photorealistic robot simulation that integrates 3D Gaussian Splatting as a drop-in renderer within vectorized physics simulators such as IsaacGym. T…
Learning a Diffusion Model Policy from Rewards via Q-Score Matching
Michael Psenka, Alejandro Escontrela, Pieter Abbeel +1
Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning. This is due to their natural ability to optimi…
Video Prediction Models as Rewards for Reinforcement Learning
Alejandro Escontrela, Ademi Adeniji, Wilson Yan +6
Specifying reward signals that allow agents to learn complex behaviors is a long-standing challenge in reinforcement learning. A promising approach is to extract preferences for be…
Barkour: Benchmarking Animal-level Agility with Quadruped Robots
Ken Caluwaerts, Atil Iscen, J. Chase Kew +41
Animals have evolved various agile locomotion strategies, such as sprinting, leaping, and jumping. There is a growing interest in developing legged robots that move like their biol…
Autonomously Untangling Long Cables
Vainavi Viswanath, Kaushik Shivakumar, Justin Kerr +7
Cables are ubiquitous in many settings and it is often useful to untangle them. However, cables are prone to self-occlusions and knots, making them difficult to perceive and manipu…
DayDreamer: World Models for Physical Robot Learning
Philipp Wu, Alejandro Escontrela, Danijar Hafner +2
To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of tria…
Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions
Alejandro Escontrela, Xue Bin Peng, Wenhao Yu +4
Training a high-dimensional simulated agent with an under-specified reward function often leads the agent to learn physically infeasible strategies that are ineffective when deploy…
A Factor-Graph Approach for Optimization Problems with Dynamics Constraints
Mandy Xie, Alejandro Escontrela, Frank Dellaert
In this paper, we introduce dynamics factor graphs as a graphical framework to solve dynamics problems and kinodynamic motion planning problems with full consideration of whole-bod…
Learning Agile Locomotion Skills with a Mentor
Atil Iscen, George Yu, Alejandro Escontrela +3
Developing agile behaviors for legged robots remains a challenging problem. While deep reinforcement learning is a promising approach, learning truly agile behaviors typically requ…
Zero-Shot Terrain Generalization for Visual Locomotion Policies
Alejandro Escontrela, George Yu, Peng Xu +2
Legged robots have unparalleled mobility on unstructured terrains. However, it remains an open challenge to design locomotion controllers that can operate in a large variety of env…