Gautam Salhotra

I am a computer science Ph.D. student in robotics & machine learning at the University of Southern California (USC), advised by Gaurav Sukhatme. Broadly, I work on combining planning algorithms with learning to achieve greater autonomy for robots, with experience in object manipulation, mobile robotics, control theory, and deep reinforcement learning.

Research interests

• Inductive biases in robot learning
• Robot autonomy in manipulation & locomotion

Select Publications

See my Google Scholar profile for a full list.

• Gautam Salhotra, Shashank Hegde, Sumeet Batra, Peter Englert, Gaurav S. Sukhatme. "Guided Learning of Robust Hurdling Policies with Curricular Trajectory Optimization". Under Review
• Gautam Salhotra^*, Christopher E. Denniston^*, David A. Caron and Gaurav S. Sukhatme. "Adaptive Sampling using POMDPs with Domain-Specific Considerations". In International Conference on Robotics and Automation (ICRA), May 2021. (PDF)
• Jun Yamada, Youngwoon Lee, Gautam Salhotra, Karl Pertsch, Max Pflueger, Gaurav S. Sukhatme, Joseph Lim and Peter Englert. "Motion Planner Augmented Reinforcement Learning for Obstructed Environments". In Conference on Robot Learning (CoRL), Nov 2020. (PDF, Website)
• Sung-Kyun Kim^*, Amanda Bouman^*, Gautam Salhotra, David D. Fan, Kyohei Otsu, Joel Burdick, Ali-akbar Agha-mohammadi. "PLGRIM: Hierarchical Value Learning for Large-scale Exploration in Unknown Environments". ICAPS 2021. (PDF)

Updates

• May 2021: Chaired the ICRA 2021 session on "Field Robotics: Control"

• Mar 2021: Our paper on adaptive sampling with POMDPs for environmental monitoring has been accepted to ICRA 2021! (PDF)

• Feb 2021: Our paper on planning for large-scale exploration in the real world has been accepted to ICAPS 2021! This is part of an ongoing collaboration with NASA JPL and Caltech for the SubT challenge. (PDF).

• Oct 2020: Our paper on augmenting reinforcement learning algorithms with motion planning has been accepted to CoRL 2020! See you at CoRL! (PDF, website).

• Aug 2020: Our paper on using robots for programming education has been accepted for publication at the American Society of Engineering Education (ASEE) Annual Conference! This was the outcome of volunteering with USC VAST to teach children and elementary school teachers programming using robots. (PDF).

• Aug-Dec 2019: Designed and TA'ed a new robotics course for Masters' students (Website).

• May-Aug 2019: I did a summer internship at Bosch Research in Sunnyvale.

• Jan 2019: Our proposal for the Amazon Research Awards was accepted! This was work with Ryan Julian to learn embeddings for tasks, so as to create composable motiions for a robot. See our lab's accepted proposals here.

• In 2018, I joined USC for a PhD in robotics!

• From 2016 to 2018, I worked in Symbotic LLC, focussing on robot manipulation. Before that, I worked for MathWorks doing technical communication and robotics projects (algorithms primarily implemented using MATLAB).