Search Results for author: Maxim Likhachev

Found 22 papers, 8 papers with code

Planning for Complex Non-prehensile Manipulation Among Movable Objects by Interleaving Multi-Agent Pathfinding and Physics-Based Simulation

no code implementations23 Mar 2023 Dhruv Mauria Saxena, Maxim Likhachev

In particular, our motivation is to allow the robot to reason over and consider non-prehensile rearrangement actions that lead to complex robot-object and object-object interactions where multiple objects might be moved by the robot simultaneously, and objects might tilt, lean on each other, or topple.

Motion Planning

Planning for Manipulation among Movable Objects: Deciding Which Objects Go Where, in What Order, and How

no code implementations23 Mar 2023 Dhruv Saxena, Maxim Likhachev

In this paper, we extend M4M and present Enhanced-M4M (E-M4M) -- a systematic graph search-based solver that searches over orderings of pushes for movable objects that need to be rearranged and different possible rearrangements of the scene.

Robot Manipulation

GePA*SE: Generalized Edge-Based Parallel A* for Slow Evaluations

1 code implementation24 Jan 2023 Shohin Mukherjee, Maxim Likhachev

However, in a number of robotics domains, the action space is heterogenous in the computational effort required to evaluate the cost of an action and its outcome.

Efficient Recovery Learning using Model Predictive Meta-Reasoning

no code implementations27 Sep 2022 Shivam Vats, Maxim Likhachev, Oliver Kroemer

We use our approach to learn recovery skills for door-opening and evaluate them both in simulation and on a real robot with little fine-tuning.

Non-Blocking Batch A* (Technical Report)

no code implementations15 Aug 2022 Rishi Veerapaneni, Maxim Likhachev

We show how this subtle but important change can lead to substantial reductions in expansions compared to the current blocking alternative, and see that the performance is related to the information difference between the batch computed NN and fast non-NN heuristic.

Effective Integration of Weighted Cost-to-go and Conflict Heuristic within Suboptimal CBS

no code implementations23 May 2022 Rishi Veerapaneni, Tushar Kusnur, Maxim Likhachev

In this paper, we show that, contrary to prevailing CBS beliefs, a weighted cost-to-go heuristic can be used effectively alongside the conflict heuristic in two possible variants.

Multi-Agent Path Finding

Enhanced Multi-Objective A* Using Balanced Binary Search Trees

1 code implementation18 Feb 2022 Zhongqiang Ren, Richard Zhan, Sivakumar Rathinam, Maxim Likhachev, Howie Choset

This work addresses a Multi-Objective Shortest Path Problem (MO-SPP) on a graph where the goal is to find a set of Pareto-optimal solutions from a start node to a destination in the graph.

On the Effectiveness of Iterative Learning Control

1 code implementation17 Nov 2021 Anirudh Vemula, Wen Sun, Maxim Likhachev, J. Andrew Bagnell

However, there is little prior theoretical work that explains the effectiveness of ILC even in the presence of large modeling errors, where optimal control methods using the misspecified model (MM) often perform poorly.

Industrial Robots

AMRA*: Anytime Multi-Resolution Multi-Heuristic A*

1 code implementation11 Oct 2021 Dhruv Mauria Saxena, Tushar Kusnur, Maxim Likhachev

A fine discretisation allows for better approximations of the continuous search space, but makes the search for a solution more computationally costly.

Motion Planning Navigate

Multi-objective Conflict-based Search Using Safe-interval Path Planning

1 code implementation2 Aug 2021 Zhongqiang Ren, Sivakumar Rathinam, Maxim Likhachev, Howie Choset

This paper addresses a generalization of the well known multi-agent path finding (MAPF) problem that optimizes multiple conflicting objectives simultaneously such as travel time and path risk.

Multi-Agent Path Finding

Multi-Objective Path-Based D* Lite

no code implementations2 Aug 2021 Zhongqiang Ren, Sivakumar Rathinam, Maxim Likhachev, Howie Choset

Incremental graph search algorithms such as D* Lite reuse previous, and perhaps partial, searches to expedite subsequent path planning tasks.

Learning Optimal Decision Making for an Industrial Truck Unloading Robot using Minimal Simulator Runs

no code implementations13 Mar 2021 Manash Pratim Das, Anirudh Vemula, Mayank Pathak, Sandip Aine, Maxim Likhachev

In this work, we investigate how would the robot with the help of a simulator, learn to maximize the number of boxes unloaded by each action.

Decision Making Multi-class Classification

Manipulation Planning Among Movable Obstacles Using Physics-Based Adaptive Motion Primitives

no code implementations8 Feb 2021 Dhruv Mauria Saxena, Muhammad Suhail Saleem, Maxim Likhachev

Unfortunately, it is infeasible to query the simulator for thousands of actions that need to be evaluated in a typical planning problem as each simulation is time-consuming.


Interleaving Graph Search and Trajectory Optimization for Aggressive Quadrotor Flight

no code implementations29 Jan 2021 Ramkumar Natarajan, Howie Choset, Maxim Likhachev

We introduce a framework for aggressive quadrotor trajectory generation with global reasoning capabilities that combines the best of trajectory optimization and discrete graph search.


Reactive Long Horizon Task Execution via Visual Skill and Precondition Models

no code implementations17 Nov 2020 Shohin Mukherjee, Chris Paxton, Arsalan Mousavian, Adam Fishman, Maxim Likhachev, Dieter Fox

Zero-shot execution of unseen robotic tasks is important to allowing robots to perform a wide variety of tasks in human environments, but collecting the amounts of data necessary to train end-to-end policies in the real-world is often infeasible.

CMAX++ : Leveraging Experience in Planning and Execution using Inaccurate Models

1 code implementation21 Sep 2020 Anirudh Vemula, J. Andrew Bagnell, Maxim Likhachev

In this paper we propose CMAX++, an approach that leverages real-world experience to improve the quality of resulting plans over successive repetitions of a robotic task.

Friction Robot Navigation

PERCH 2.0 : Fast and Accurate GPU-based Perception via Search for Object Pose Estimation

no code implementations1 Aug 2020 Aditya Agarwal, Yupeng Han, Maxim Likhachev

We show that our approach can achieve a speedup of 100x over PERCH, as well as better accuracy than the state-of-the-art data-driven approaches on 6-DoF pose estimation without the need for annotating ground truth poses in the training data.

Pose Estimation Robotic Grasping

Multi-Resolution A*

no code implementations14 Apr 2020 Wei Du, Fahad Islam, Maxim Likhachev

We show that MRA* is bounded suboptimal with respect to the anchor resolution search space and resolution complete.

Motion Planning

Planning and Execution using Inaccurate Models with Provable Guarantees

1 code implementation9 Mar 2020 Anirudh Vemula, Yash Oza, J. Andrew Bagnell, Maxim Likhachev

In this paper, we propose CMAX an approach for interleaving planning and execution.

Driving in Dense Traffic with Model-Free Reinforcement Learning

2 code implementations15 Sep 2019 Dhruv Mauria Saxena, Sangjae Bae, Alireza Nakhaei, Kikuo Fujimura, Maxim Likhachev

Traditional planning and control methods could fail to find a feasible trajectory for an autonomous vehicle to execute amongst dense traffic on roads.

Continuous Control reinforcement-learning +1

PERCH: Perception via Search for Multi-Object Recognition and Localization

no code implementations19 Oct 2015 Venkatraman Narayanan, Maxim Likhachev

In many robotic domains such as flexible automated manufacturing or personal assistance, a fundamental perception task is that of identifying and localizing objects whose 3D models are known.

Object Recognition Scene Generation

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