Search Results for author: Rohan Chandra

Found 31 papers, 14 papers with code

Reward Is Enough: LLMs Are In-Context Reinforcement Learners

no code implementations21 May 2025 Kefan Song, Amir Moeini, Peng Wang, Lei Gong, Rohan Chandra, Yanjun Qi, Shangtong Zhang

At the next round, we prompt the LLM again with the same task and a context consisting of all previous responses and rewards.

Large Language Model Reinforcement Learning (RL) +1

Experience Replay Addresses Loss of Plasticity in Continual Learning

no code implementations25 Mar 2025 Jiuqi Wang, Rohan Chandra, Shangtong Zhang

The main contribution of this paper is to propose a new hypothesis that experience replay addresses the loss of plasticity in continual learning.

Continual Learning In-Context Learning

Towards Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward Models

no code implementations10 Mar 2025 Kefan Song, Jin Yao, Runnan Jiang, Rohan Chandra, Shangtong Zhang

By using expert-written text from arXiv, we are able to benchmark the group fairness of reward models without requiring the same prompt questions across different demographic groups.

All Benchmarking +1

A Survey of In-Context Reinforcement Learning

no code implementations11 Feb 2025 Amir Moeini, Jiuqi Wang, Jacob Beck, Ethan Blaser, Shimon Whiteson, Rohan Chandra, Shangtong Zhang

Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters.

In-Context Reinforcement Learning reinforcement-learning +3

DAVE: Diverse Atomic Visual Elements Dataset with High Representation of Vulnerable Road Users in Complex and Unpredictable Environments

no code implementations28 Dec 2024 Xijun Wang, Pedro Sandoval-Segura, ChengYuan Zhang, Junyun Huang, Tianrui Guan, Ruiqi Xian, Fuxiao Liu, Rohan Chandra, Boqing Gong, Dinesh Manocha

Addressing this gap, we present a new dataset, DAVE, designed for evaluating perception methods with high representation of Vulnerable Road Users (VRUs: e. g. pedestrians, animals, motorbikes, and bicycles) in complex and unpredictable environments.

Action Recognition Moment Retrieval +2

Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes

no code implementations7 Aug 2024 Chen Tang, Ben Abbatematteo, Jiaheng Hu, Rohan Chandra, Roberto Martín-Martín, Peter Stone

Reinforcement learning (RL), particularly its combination with deep neural networks referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of sophisticated robotic behaviors.

Deep Reinforcement Learning Reinforcement Learning (RL) +1

Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds

no code implementations26 May 2024 Rohan Chandra, Haresh Karnan, Negar Mehr, Peter Stone, Joydeep Biswas

In this paper, we present a new multi-agent maximum entropy inverse reinforcement learning algorithm for real world unstructured pedestrian crowds.

Imitation Learning Motion Planning +2

Neural Differentiable Integral Control Barrier Functions for Unknown Nonlinear Systems with Input Constraints

no code implementations12 Dec 2023 Vrushabh Zinage, Rohan Chandra, Efstathios Bakolas

In this paper, we propose a deep learning based control synthesis framework for fast and online computation of controllers that guarantees the safety of general nonlinear control systems with unknown dynamics in the presence of input constraints.

Imitation Learning

Disturbance Observer-based Robust Integral Control Barrier Functions for Nonlinear Systems with High Relative Degree

1 code implementation29 Sep 2023 Vrushabh Zinage, Rohan Chandra, Efstathios Bakolas

Towards this aim, we first construct a governing augmented state space model consisting of the equations of motion of the original system, the integral control law and the nonlinear disturbance observer.

Decentralized Social Navigation with Non-Cooperative Robots via Bi-Level Optimization

1 code implementation15 Jun 2023 Rohan Chandra, Rahul Menon, Zayne Sprague, Arya Anantula, Joydeep Biswas

This paper presents a fully decentralized approach for realtime non-cooperative multi-robot navigation in social mini-games, such as navigating through a narrow doorway or negotiating right of way at a corridor intersection.

Collision Avoidance Multi-agent Reinforcement Learning +3

SOCIALMAPF: Optimal and Efficient Multi-Agent Path Finding with Strategic Agents for Social Navigation

no code implementations15 Oct 2022 Rohan Chandra, Rahul Maligi, Arya Anantula, Joydeep Biswas

We perform an extensive array of experiments that show that optimal search-based MAPF techniques lead to collisions and increased time-to-goal in SocialMAPF compared to our proposed method using mechanism design.

Motion Planning Multi-Agent Path Finding +1

M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers

1 code implementation24 Apr 2021 Tianrui Guan, Jun Wang, Shiyi Lan, Rohan Chandra, Zuxuan Wu, Larry Davis, Dinesh Manocha

We present a novel architecture for 3D object detection, M3DeTR, which combines different point cloud representations (raw, voxels, bird-eye view) with different feature scales based on multi-scale feature pyramids.

3D Object Detection object-detection +1

GANav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environments

1 code implementation7 Mar 2021 Tianrui Guan, Divya Kothandaraman, Rohan Chandra, Adarsh Jagan Sathyamoorthy, Kasun Weerakoon, Dinesh Manocha

We interface GANav with a deep reinforcement learning-based navigation algorithm and highlight its benefits in terms of navigation in real-world unstructured terrains.

Deep Reinforcement Learning Robot Navigation +1

B-GAP: Behavior-Rich Simulation and Navigation for Autonomous Driving

3 code implementations7 Nov 2020 Angelos Mavrogiannis, Rohan Chandra, Dinesh Manocha

We address the problem of ego-vehicle navigation in dense simulated traffic environments populated by road agents with varying driver behaviors.

Robotics

Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cues

no code implementations14 Mar 2020 Trisha Mittal, Uttaran Bhattacharya, Rohan Chandra, Aniket Bera, Dinesh Manocha

Additionally, we extract and compare affective cues corresponding to perceived emotion from the two modalities within a video to infer whether the input video is "real" or "fake".

DeepFake Detection Face Swapping +1

Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs

no code implementations arXiv 2019 Rohan Chandra, Tianrui Guan, Srujan Panuganti, Trisha Mittal, Uttaran Bhattacharya, Aniket Bera, Dinesh Manocha

In practice, our approach reduces the average prediction error by more than 54% over prior algorithms and achieves a weighted average accuracy of 91. 2% for behavior prediction.

Robotics

M3ER: Multiplicative Multimodal Emotion Recognition Using Facial, Textual, and Speech Cues

no code implementations9 Nov 2019 Trisha Mittal, Uttaran Bhattacharya, Rohan Chandra, Aniket Bera, Dinesh Manocha

Our approach combines cues from multiple co-occurring modalities (such as face, text, and speech) and also is more robust than other methods to sensor noise in any of the individual modalities.

Multimodal Emotion Recognition

STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits

1 code implementation28 Oct 2019 Uttaran Bhattacharya, Trisha Mittal, Rohan Chandra, Tanmay Randhavane, Aniket Bera, Dinesh Manocha

We use hundreds of annotated real-world gait videos and augment them with thousands of annotated synthetic gaits generated using a novel generative network called STEP-Gen, built on an ST-GCN based Conditional Variational Autoencoder (CVAE).

General Classification

RobustTP: End-to-End Trajectory Prediction for Heterogeneous Road-Agents in Dense Traffic with Noisy Sensor Inputs

1 code implementation20 Jul 2019 Rohan Chandra, Uttaran Bhattacharya, Christian Roncal, Aniket Bera, Dinesh Manocha

RobustTP is an approach that first computes trajectories using a combination of a non-linear motion model and a deep learning-based instance segmentation algorithm.

Robotics

RoadTrack: Realtime Tracking of Road Agents in Dense and Heterogeneous Environments

1 code implementation25 Jun 2019 Rohan Chandra, Uttaran Bhattacharya, Tanmay Randhavane, Aniket Bera, Dinesh Manocha

We present a realtime tracking algorithm, RoadTrack, to track heterogeneous road-agents in dense traffic videos.

Robotics

TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions

2 code implementations CVPR 2019 Rohan Chandra, Uttaran Bhattacharya, Aniket Bera, Dinesh Manocha

We evaluate the performance of our prediction algorithm, TraPHic, on the standard datasets and also introduce a new dense, heterogeneous traffic dataset corresponding to urban Asian videos and agent trajectories.

Trajectory Prediction Robotics

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